{ "benchmark_line": "gamebench2", "comparability_tuples": [ { "evaluation_family": "codegen_public_benchmark", "rating_method": "sequential_elo", "reasoning_effort": "balanced", "results_cut_id": "20260727_140229", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": "20260727_140229", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": "20260727_140229", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": "20260727_140229", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": "20260727_140229", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_kind": "overall" } ], "generated_at": "2026-07-27T14:02:29Z", "public_release_id": "gb2-20260727-b63faa64fdbb", "results_cut_id": "gb2-20260727-b63faa64fdbb", "rows": [ { "admitted_plugins": 8, "attempted_matches": 462, "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-2026-07-25": 11 }, "run_count": 8, "token_priced_attempt_count": 11, "total": 12.66097 }, "codegen_evaluated_cells": 8, "conditional_success_score": 83.35493107640038, "contributing_entrants": null, "distinct_rated_opponents": 231, "draws": 65, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04" ], "infra_failures_excluded": 4, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:46:35Z", "losses": 78, "max_score": 100.0, "measured_at": null, "min_score": 61.59421983387494, "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 462, "rating_method": "sequential_elo", "raw_elo": 1732.2058050532637, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 83.35493107640038, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 319 }, { "admitted_plugins": 13, "attempted_matches": 520, "capped_draws": 0, "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": 1.320515, "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": 77.44179232176744, "contributing_entrants": null, "distinct_rated_opponents": 260, "draws": 40, "entry_count": 13, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-26T05:19:34Z", "losses": 100, "max_score": 99.01057790596052, "measured_at": null, "min_score": 63.18013490216033, "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 520, "rating_method": "sequential_elo", "raw_elo": 1757.36248030638, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 73.52435752053414, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 380 }, { "admitted_plugins": 8, "attempted_matches": 486, "capped_draws": 22, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 9 }, "evidence_basis": "Standard list-price estimate", "max": 3.2933475, "mean": 2.642580625, "median": 2.681945, "min": 1.562975, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 21.140644999999996 }, "codegen_evaluated_cells": 8, "conditional_success_score": 71.82613215131099, "contributing_entrants": null, "distinct_rated_opponents": 243, "draws": 101, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:53:35Z", "losses": 87, "max_score": 100.0, "measured_at": null, "min_score": 38.52438727472494, "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 486, "rating_method": "sequential_elo", "raw_elo": 1705.7578706039046, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 71.82613215131099, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 298 }, { "admitted_plugins": 14, "attempted_matches": 710, "capped_draws": 7, "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": 0.4461796875, "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": 71.8966107628626, "contributing_entrants": null, "distinct_rated_opponents": 355, "draws": 99, "entry_count": 14, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:10:13Z", "losses": 180, "max_score": 91.93118700577348, "measured_at": null, "min_score": 43.019463779962486, "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": 710, "rating_method": "sequential_elo", "raw_elo": 1702.303798928371, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 69.53611634620681, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 431 }, { "admitted_plugins": 7, "attempted_matches": 430, "capped_draws": 30, "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-2026-07-25": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 21.885474999999996 }, "codegen_evaluated_cells": 8, "conditional_success_score": 67.9471088226076, "contributing_entrants": null, "distinct_rated_opponents": 215, "draws": 95, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:37:21Z", "losses": 94, "max_score": 88.73890042665397, "measured_at": null, "min_score": 30.738052083219, "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": 429, "rating_method": "sequential_elo", "raw_elo": 1678.5115903938529, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 65.71628362373028, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 240 }, { "admitted_plugins": 8, "attempted_matches": 488, "capped_draws": 12, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 8 }, "evidence_basis": "Standard list-price estimate", "max": 12.915325, "mean": 10.059243749999998, "median": 10.0094025, "min": 8.401555, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 80.47395 }, "codegen_evaluated_cells": 8, "conditional_success_score": 65.25243558332285, "contributing_entrants": null, "distinct_rated_opponents": 244, "draws": 58, "entry_count": 8, "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 }, "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": "2026-07-27T11:45:56Z", "losses": 137, "max_score": 100.0, "measured_at": null, "min_score": 16.21797777560009, "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 488, "rating_method": "sequential_elo", "raw_elo": 1631.458664413848, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 65.25243558332285, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 293 }, { "admitted_plugins": 7, "attempted_matches": 388, "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-2026-07-25": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 4.0371999999999995 }, "codegen_evaluated_cells": 8, "conditional_success_score": 65.00100860904149, "contributing_entrants": null, "distinct_rated_opponents": 194, "draws": 59, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:25:35Z", "losses": 108, "max_score": 76.52631679447857, "measured_at": null, "min_score": 49.32044382130511, "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 388, "rating_method": "sequential_elo", "raw_elo": 1646.7741909355173, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 62.86690915330064, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 221 }, { "admitted_plugins": 23, "attempted_matches": 1502, "capped_draws": 42, "codegen_cost_usd": { "admitted_cell_count": 23, "cell_count": 8, "cost_basis_counts": { "provider_reported": 39 }, "evidence_basis": "Provider-reported", "failed_cell_count": 1, "max": 0.12366493333333332, "mean": 0.09185773333333332, "median": 0.09170913333333332, "min": 0.04980146666666666, "recorded_attempt_count": 39, "run_count": 24, "total": 2.2045855999999997 }, "codegen_evaluated_cells": 24, "conditional_success_score": 60.64883527347195, "contributing_entrants": null, "distinct_rated_opponents": 750, "draws": 344, "entry_count": 23, "failed_game_aliases": [ "GB2-02" ], "first_pass_admitted": 10, "first_pass_rate": 0.4166666666666667, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "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": "2026-07-27T11:52:52Z", "losses": 416, "max_score": 84.85770377828395, "measured_at": null, "min_score": 37.60021583373031, "model_code_failure_rate": 0.041666666666666664, "model_code_failures": 1, "model_display_name": "Grok 4.5", "model_slug": "x-ai-grok-4-5", "plugin_success_rate": 0.9583333333333334, "provider": "xAI", "provider_key": "x-ai", "rank": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1502, "rating_method": "sequential_elo", "raw_elo": 1615.257839866562, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 13, "repaired_rate": 0.5416666666666666, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 60.006958322299816, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 742 }, { "admitted_plugins": 13, "attempted_matches": 662, "capped_draws": 44, "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": 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": 61.77904448694649, "contributing_entrants": null, "distinct_rated_opponents": 331, "draws": 153, "entry_count": 13, "failed_game_aliases": [ "GB2-06", "GB2-07", "GB2-08" ], "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:48:28Z", "losses": 166, "max_score": 82.43652527134509, "measured_at": null, "min_score": 48.05298165377025, "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 662, "rating_method": "sequential_elo", "raw_elo": 1657.548139470911, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 58.65391822625071, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 343 }, { "admitted_plugins": 8, "attempted_matches": 442, "capped_draws": 7, "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": 0.6689649999999999, "mean": 0.46799875, "median": 0.4352825, "min": 0.366615, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 10 }, "run_count": 9, "token_priced_attempt_count": 10, "total": 4.1199200000000005 }, "codegen_evaluated_cells": 9, "conditional_success_score": 59.573031480400935, "contributing_entrants": null, "distinct_rated_opponents": 221, "draws": 101, "entry_count": 8, "failed_game_aliases": [ "GB2-06" ], "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 }, "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": "2026-07-27T11:52:52Z", "losses": 122, "max_score": 74.1340312841928, "measured_at": null, "min_score": 34.15864897798004, "model_code_failure_rate": 0.1111111111111111, "model_code_failures": 1, "model_display_name": "GPT-5.6 Sol", "model_slug": "gpt-5-6-sol", "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": 442, "rating_method": "sequential_elo", "raw_elo": 1602.640138463198, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.1111111111111111, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 57.844433198792, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 492, "capped_draws": 21, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 11 }, "evidence_basis": "Standard list-price estimate", "max": 12.13752, "mean": 8.1660015625, "median": 8.18098, "min": 4.7142525, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 11 }, "run_count": 8, "token_priced_attempt_count": 11, "total": 65.3280125 }, "codegen_evaluated_cells": 8, "conditional_success_score": 54.627943464276825, "contributing_entrants": null, "distinct_rated_opponents": 246, "draws": 96, "entry_count": 8, "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 }, "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": "2026-07-27T11:53:51Z", "losses": 167, "max_score": 72.98349769903467, "measured_at": null, "min_score": 42.877873486874975, "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 492, "rating_method": "sequential_elo", "raw_elo": 1576.1527501926316, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 54.627943464276825, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 504, "capped_draws": 53, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 10 }, "evidence_basis": "Standard list-price estimate", "max": 0.1598575, "mean": 0.093565, "median": 0.07461, "min": 0.06826499999999999, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 10 }, "run_count": 8, "token_priced_attempt_count": 10, "total": 0.7485199999999999 }, "codegen_evaluated_cells": 8, "conditional_success_score": 52.68516521787668, "contributing_entrants": null, "distinct_rated_opponents": 252, "draws": 195, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:23Z", "losses": 104, "max_score": 90.56767341997636, "measured_at": null, "min_score": 29.70399047704974, "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 504, "rating_method": "sequential_elo", "raw_elo": 1573.98087527373, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 52.68516521787668, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 205 }, { "admitted_plugins": 8, "attempted_matches": 454, "capped_draws": 57, "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": 52.00774565635941, "contributing_entrants": null, "distinct_rated_opponents": 226, "draws": 159, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:57Z", "losses": 112, "max_score": 89.02948337376621, "measured_at": null, "min_score": 21.05198164014908, "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 452, "rating_method": "sequential_elo", "raw_elo": 1565.2269025940584, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 8, "repaired_rate": 1.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 52.00774565635941, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 181 }, { "admitted_plugins": 8, "attempted_matches": 470, "capped_draws": 7, "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": 4.987857, "mean": 3.1645696249999995, "median": 3.0710854999999997, "min": 1.985613, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 10 }, "run_count": 9, "token_priced_attempt_count": 10, "total": 28.806540999999996 }, "codegen_evaluated_cells": 9, "conditional_success_score": 51.77615652783872, "contributing_entrants": null, "distinct_rated_opponents": 235, "draws": 132, "entry_count": 8, "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 }, "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": "2026-07-27T11:37:21Z", "losses": 154, "max_score": 75.31262484978316, "measured_at": null, "min_score": 28.573734971782702, "model_code_failure_rate": 0.1111111111111111, "model_code_failures": 1, "model_display_name": "GPT-5.6 Luna", "model_slug": "gpt-5-6-luna", "plugin_success_rate": 0.8888888888888888, "provider": "OpenAI", "provider_key": "openai", "rank": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 470, "rating_method": "sequential_elo", "raw_elo": 1558.4439764910153, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 1, "repaired_rate": 0.1111111111111111, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 50.27379592979224, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 20, "attempted_matches": 716, "capped_draws": 18, "codegen_cost_usd": { "admitted_cell_count": 20, "cell_count": 8, "cost_basis_counts": { "provider_reported": 37 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.14454373333333334, "mean": 0.08818255, "median": 0.07401653333333333, "min": 0.052337466666666665, "recorded_attempt_count": 37, "run_count": 24, "total": 2.1163812 }, "codegen_evaluated_cells": 24, "conditional_success_score": 51.65268475219032, "contributing_entrants": null, "distinct_rated_opponents": 358, "draws": 257, "entry_count": 40, "failed_game_aliases": [ "GB2-02", "GB2-03", "GB2-05" ], "first_pass_admitted": 12, "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 }, "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": "2026-07-27T11:53:35Z", "losses": 472, "max_score": 64.63299103911847, "measured_at": null, "min_score": 22.814064655201765, "model_code_failure_rate": 0.16666666666666666, "model_code_failures": 4, "model_display_name": "Grok 4.5", "model_slug": "x-ai-grok-4-5", "plugin_success_rate": 0.8333333333333334, "provider": "xAI", "provider_key": "x-ai", "rank": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 716, "rating_method": "sequential_elo", "raw_elo": 1562.5568848125563, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 8, "repaired_rate": 0.3333333333333333, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 49.35118534448464, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 697 }, { "admitted_plugins": 16, "attempted_matches": 1025, "capped_draws": 127, "codegen_cost_usd": { "admitted_cell_count": 16, "cell_count": 8, "cost_basis_counts": { "provider_reported": 29 }, "evidence_basis": "Provider-reported", "max": 0.25698975, "mean": 0.172479834375, "median": 0.166217925, "min": 0.10864875, "recorded_attempt_count": 29, "run_count": 16, "total": 2.75967735 }, "codegen_evaluated_cells": 16, "conditional_success_score": 49.29082044256339, "contributing_entrants": null, "distinct_rated_opponents": 512, "draws": 379, "entry_count": 16, "failed_game_aliases": [], "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:37:40Z", "losses": 261, "max_score": 79.77925593934339, "measured_at": null, "min_score": 22.174040290361702, "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1024, "rating_method": "sequential_elo", "raw_elo": 1549.0656151440612, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 12, "repaired_rate": 0.75, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 49.29082044256339, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 384 }, { "admitted_plugins": 16, "attempted_matches": 570, "capped_draws": 42, "codegen_cost_usd": { "admitted_cell_count": 16, "cell_count": 8, "cost_basis_counts": { "provider_reported": 17 }, "evidence_basis": "Provider-reported", "max": 0.0820533, "mean": 0.0699502125, "median": 0.06609614999999999, "min": 0.0587988, "recorded_attempt_count": 17, "run_count": 16, "total": 1.1192034 }, "codegen_evaluated_cells": 16, "conditional_success_score": 48.725624144182824, "contributing_entrants": null, "distinct_rated_opponents": 285, "draws": 286, "entry_count": 27, "failed_game_aliases": [], "first_pass_admitted": 15, "first_pass_rate": 0.9375, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": 243, "max_score": 65.37732935727273, "measured_at": null, "min_score": 26.098699501503095, "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 570, "rating_method": "sequential_elo", "raw_elo": 1562.656448549823, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": 1, "repaired_rate": 0.0625, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 48.725624144182824, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 403 }, { "admitted_plugins": 8, "attempted_matches": 478, "capped_draws": 47, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 9 }, "evidence_basis": "Standard list-price estimate", "max": 0.712055, "mean": 0.49864374999999994, "median": 0.5065824999999999, "min": 0.29423750000000004, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 3.989149999999999 }, "codegen_evaluated_cells": 8, "conditional_success_score": 48.349371100347874, "contributing_entrants": null, "distinct_rated_opponents": 239, "draws": 179, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:56Z", "losses": 129, "max_score": 90.34672640532096, "measured_at": null, "min_score": 25.753419845975525, "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": 478, "rating_method": "sequential_elo", "raw_elo": 1545.839712781073, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 48.349371100347874, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 170 }, { "admitted_plugins": 7, "attempted_matches": 422, "capped_draws": 6, "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-2026-07-25": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 7.44989 }, "codegen_evaluated_cells": 8, "conditional_success_score": 49.82574174672981, "contributing_entrants": null, "distinct_rated_opponents": 211, "draws": 59, "entry_count": 7, "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 }, "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": "2026-07-27T11:53:30Z", "losses": 123, "max_score": 49.82574174672981, "measured_at": null, "min_score": 49.82574174672981, "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 422, "rating_method": "sequential_elo", "raw_elo": 1636.395785460338, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 48.18987346377536, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 240 }, { "admitted_plugins": 8, "attempted_matches": 450, "capped_draws": 65, "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": 0.442856875, "median": 0.4176025, "min": 0.34269, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 3.5428550000000003 }, "codegen_evaluated_cells": 8, "conditional_success_score": 48.01639254386449, "contributing_entrants": null, "distinct_rated_opponents": 225, "draws": 152, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:58Z", "losses": 142, "max_score": 65.72170653066799, "measured_at": null, "min_score": 27.47820671040979, "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 450, "rating_method": "sequential_elo", "raw_elo": 1539.8710077025632, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 48.01639254386449, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 156 }, { "admitted_plugins": 18, "attempted_matches": 726, "capped_draws": 80, "codegen_cost_usd": { "admitted_cell_count": 18, "cell_count": 8, "cost_basis_counts": { "provider_reported": 48 }, "evidence_basis": "Provider-reported", "failed_cell_count": 5, "max": 0.9392418, "mean": 0.7382814249999998, "median": 0.7264120999999999, "min": 0.4980382, "recorded_attempt_count": 48, "run_count": 23, "total": 16.779512399999998 }, "codegen_evaluated_cells": 23, "conditional_success_score": 50.66737638021479, "contributing_entrants": null, "distinct_rated_opponents": 363, "draws": 412, "entry_count": 36, "failed_game_aliases": [ "GB2-03", "GB2-05", "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 }, "infra_excluded_game_aliases": [ "GB2-02", "GB2-08" ], "infra_failures_excluded": 3, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:54:18Z", "losses": 407, "max_score": 53.439927382671186, "measured_at": null, "min_score": 46.192829786225445, "model_code_failure_rate": 0.21739130434782608, "model_code_failures": 5, "model_display_name": "Kimi K3", "model_slug": "moonshotai-kimi-k3", "plugin_success_rate": 0.782608695652174, "provider": "Moonshot", "provider_key": "moonshotai", "rank": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 725, "rating_method": "sequential_elo", "raw_elo": 1535.4007037331653, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Max", "reasoning_bracket": "intensive", "reasoning_bucket": "max", "reasoning_bucket_label": "Max", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "max" }, "repaired_admitted": 18, "repaired_rate": 0.782608695652174, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 47.65567044796971, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 528 }, { "admitted_plugins": 8, "attempted_matches": 458, "capped_draws": 72, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 9 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 1, "max": 0.046574, "mean": 0.036155625, "median": 0.035338, "min": 0.025803, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 9 }, "run_count": 9, "token_priced_attempt_count": 9, "total": 0.315048 }, "codegen_evaluated_cells": 9, "conditional_success_score": 48.244974243672814, "contributing_entrants": null, "distinct_rated_opponents": 229, "draws": 204, "entry_count": 8, "failed_game_aliases": [ "GB2-06" ], "first_pass_admitted": 8, "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 }, "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": "2026-07-27T11:44:52Z", "losses": 125, "max_score": 65.00304603642252, "measured_at": null, "min_score": 30.997988769059855, "model_code_failure_rate": 0.1111111111111111, "model_code_failures": 1, "model_display_name": "GPT-5.6 Luna", "model_slug": "gpt-5-6-luna", "plugin_success_rate": 0.8888888888888888, "provider": "OpenAI", "provider_key": "openai", "rank": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 458, "rating_method": "sequential_elo", "raw_elo": 1531.3726221137415, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 46.8450760430698, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 129 }, { "admitted_plugins": 12, "attempted_matches": 762, "capped_draws": 56, "codegen_cost_usd": { "admitted_cell_count": 12, "cell_count": 7, "cost_basis_counts": { "local_standard_estimate": 15 }, "evidence_basis": "Standard list-price estimate", "max": 1.5164726249999998, "mean": 1.0182428035714286, "median": 0.9670455, "min": 0.8356068750000001, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 15 }, "run_count": 12, "token_priced_attempt_count": 15, "total": 12.214044 }, "codegen_evaluated_cells": 12, "conditional_success_score": 46.5489701837238, "contributing_entrants": null, "distinct_rated_opponents": 381, "draws": 205, "entry_count": 12, "failed_game_aliases": [], "first_pass_admitted": 10, "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 }, "infra_excluded_game_aliases": [ "GB2-01", "GB2-03", "GB2-04" ], "infra_failures_excluded": 6, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:53:30Z", "losses": 271, "max_score": 66.30476749736133, "measured_at": null, "min_score": 29.44411630713003, "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 762, "rating_method": "sequential_elo", "raw_elo": 1521.9931594970951, "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-mini", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 2, "repaired_rate": 0.16666666666666666, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 46.5489701837238, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 286 }, { "admitted_plugins": 8, "attempted_matches": 468, "capped_draws": 52, "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-2026-07-25": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 0.97393 }, "codegen_evaluated_cells": 8, "conditional_success_score": 46.10653397009744, "contributing_entrants": null, "distinct_rated_opponents": 234, "draws": 163, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": 141, "max_score": 57.75514722037097, "measured_at": null, "min_score": 35.54624651592337, "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": 468, "rating_method": "sequential_elo", "raw_elo": 1515.5555083722368, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking field omitted", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking field omitted", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 46.10653397009744, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 164 }, { "admitted_plugins": 8, "attempted_matches": 420, "capped_draws": 63, "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-2026-07-25": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 1.743525 }, "codegen_evaluated_cells": 8, "conditional_success_score": 45.15308829494262, "contributing_entrants": null, "distinct_rated_opponents": 210, "draws": 161, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:56Z", "losses": 117, "max_score": 76.32595670280091, "measured_at": null, "min_score": 26.60687800872694, "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 420, "rating_method": "sequential_elo", "raw_elo": 1526.0659801878735, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 45.15308829494262, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 142 }, { "admitted_plugins": 16, "attempted_matches": 578, "capped_draws": 37, "codegen_cost_usd": { "admitted_cell_count": 16, "cell_count": 8, "cost_basis_counts": { "provider_reported": 28 }, "evidence_basis": "Provider-reported", "max": 0.116343, "mean": 0.07787519999999999, "median": 0.0843883, "min": 0.041110400000000005, "recorded_attempt_count": 28, "run_count": 16, "total": 1.2460032 }, "codegen_evaluated_cells": 16, "conditional_success_score": 45.1145758243171, "contributing_entrants": null, "distinct_rated_opponents": 289, "draws": 308, "entry_count": 28, "failed_game_aliases": [], "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:44:21Z", "losses": 255, "max_score": 74.68590448880083, "measured_at": null, "min_score": 19.6056169247618, "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 578, "rating_method": "sequential_elo", "raw_elo": 1555.2018958252147, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": 11, "repaired_rate": 0.6875, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 45.1145758243171, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 369 }, { "admitted_plugins": 8, "attempted_matches": 488, "capped_draws": 27, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 9 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 1, "max": 0.147405, "mean": 0.121464375, "median": 0.124865, "min": 0.09045, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 9 }, "run_count": 9, "token_priced_attempt_count": 9, "total": 1.069485 }, "codegen_evaluated_cells": 9, "conditional_success_score": 46.415421721995585, "contributing_entrants": null, "distinct_rated_opponents": 244, "draws": 132, "entry_count": 8, "failed_game_aliases": [ "GB2-04" ], "first_pass_admitted": 8, "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 }, "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": "2026-07-27T11:59:44Z", "losses": 171, "max_score": 57.49104851229338, "measured_at": null, "min_score": 31.688519104226355, "model_code_failure_rate": 0.1111111111111111, "model_code_failures": 1, "model_display_name": "GPT-5.6 Sol", "model_slug": "gpt-5-6-sol", "plugin_success_rate": 0.8888888888888888, "provider": "OpenAI", "provider_key": "openai", "rank": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 488, "rating_method": "sequential_elo", "raw_elo": 1516.3012269685896, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 45.06861065270844, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 185 }, { "admitted_plugins": 10, "attempted_matches": 620, "capped_draws": 62, "codegen_cost_usd": { "admitted_cell_count": 10, "cell_count": 8, "cost_basis_counts": { "local_list_price_estimate": 10 }, "evidence_basis": "Standard list-price estimate", "max": 0.4567, "mean": 0.3660333333333334, "median": 0.355077, "min": 0.234622, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 2, "boardgame-list-prices-2026-07-25": 8 }, "run_count": 10, "token_priced_attempt_count": 10, "total": 3.5443079999999996 }, "codegen_evaluated_cells": 10, "conditional_success_score": 44.835133203247864, "contributing_entrants": null, "distinct_rated_opponents": 310, "draws": 194, "entry_count": 10, "failed_game_aliases": [], "first_pass_admitted": 10, "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 }, "infra_excluded_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "GB2-05", "GB2-06", "GB2-07", "GB2-08" ], "infra_failures_excluded": 18, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:48:31Z", "losses": 217, "max_score": 58.84535558133786, "measured_at": null, "min_score": 31.86645017234374, "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 620, "rating_method": "sequential_elo", "raw_elo": 1507.2177594422292, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 44.835133203247864, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 400, "capped_draws": 14, "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-2026-07-25": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 1.262825 }, "codegen_evaluated_cells": 8, "conditional_success_score": 46.142255589163746, "contributing_entrants": null, "distinct_rated_opponents": 200, "draws": 95, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:54:26Z", "losses": 134, "max_score": 59.81731792757247, "measured_at": null, "min_score": 28.009047114593564, "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 400, "rating_method": "sequential_elo", "raw_elo": 1527.4487367440902, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking field omitted", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking field omitted", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 44.62732274970943, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 171 }, { "admitted_plugins": 12, "attempted_matches": 768, "capped_draws": 150, "codegen_cost_usd": { "admitted_cell_count": 12, "cell_count": 8, "cost_basis_counts": { "provider_reported": 23 }, "evidence_basis": "Provider-reported", "failed_cell_count": 2, "max": 0.00407402, "mean": 0.00223773125, "median": 0.00220356, "min": 0.00093502, "recorded_attempt_count": 23, "run_count": 14, "total": 0.03065926 }, "codegen_evaluated_cells": 14, "conditional_success_score": 45.77503697260136, "contributing_entrants": null, "distinct_rated_opponents": 384, "draws": 249, "entry_count": 12, "failed_game_aliases": [ "GB2-02", "GB2-04" ], "first_pass_admitted": 6, "first_pass_rate": 0.42857142857142855, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [ "GB2-04", "GB2-06" ], "infra_failures_excluded": 2, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:55:02Z", "losses": 265, "max_score": 58.36812405939523, "measured_at": null, "min_score": 23.723344738770017, "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 768, "rating_method": "sequential_elo", "raw_elo": 1483.2342243122505, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 6, "repaired_rate": 0.42857142857142855, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 44.04453267378009, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 7, "attempted_matches": 416, "capped_draws": 67, "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": 0.0216425, "min": 0.015285, "recorded_attempt_count": 9, "run_count": 8, "total": 0.18239875 }, "codegen_evaluated_cells": 8, "conditional_success_score": 45.267658771883625, "contributing_entrants": null, "distinct_rated_opponents": 208, "draws": 149, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:32Z", "losses": 136, "max_score": 78.20945134532496, "measured_at": null, "min_score": 30.15214880984472, "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 416, "rating_method": "sequential_elo", "raw_elo": 1512.8649532761392, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 43.78144051135187, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 131 }, { "admitted_plugins": 6, "attempted_matches": 384, "capped_draws": 66, "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": 45.7754669580277, "contributing_entrants": null, "distinct_rated_opponents": 192, "draws": 90, "entry_count": 6, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:53:51Z", "losses": 144, "max_score": 76.49983872640665, "measured_at": null, "min_score": 23.38150584800255, "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": 384, "rating_method": "sequential_elo", "raw_elo": 1522.0401416715802, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 42.598871978808184, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 150 }, { "admitted_plugins": 8, "attempted_matches": 496, "capped_draws": 81, "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-2026-07-25": 10 }, "run_count": 9, "token_priced_attempt_count": 10, "total": 0.6063375 }, "codegen_evaluated_cells": 9, "conditional_success_score": 43.59133189692441, "contributing_entrants": null, "distinct_rated_opponents": 247, "draws": 221, "entry_count": 8, "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 }, "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": "2026-07-27T11:59:44Z", "losses": 149, "max_score": 56.16041187613398, "measured_at": null, "min_score": 28.668609009228703, "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 496, "rating_method": "sequential_elo", "raw_elo": 1494.723063280869, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 1, "repaired_rate": 0.1111111111111111, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 42.326465907439584, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 126 }, { "admitted_plugins": 8, "attempted_matches": 294, "capped_draws": 35, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 10 }, "evidence_basis": "Standard list-price estimate", "max": 0.454645, "mean": 0.28201406249999994, "median": 0.2695775, "min": 0.17401125, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 10 }, "run_count": 8, "token_priced_attempt_count": 10, "total": 2.2561125 }, "codegen_evaluated_cells": 8, "conditional_success_score": 42.010776110623965, "contributing_entrants": null, "distinct_rated_opponents": 147, "draws": 166, "entry_count": 16, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:54:22Z", "losses": 172, "max_score": 62.019294143192774, "measured_at": null, "min_score": 24.622792993226422, "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 293, "rating_method": "sequential_elo", "raw_elo": 1518.3720508554893, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 42.010776110623965, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 1, "wins": 183 }, { "admitted_plugins": 8, "attempted_matches": 438, "capped_draws": 53, "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": 0.158095, "min": 0.108735, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 11 }, "run_count": 8, "token_priced_attempt_count": 11, "total": 1.3395199999999998 }, "codegen_evaluated_cells": 8, "conditional_success_score": 41.99986875925433, "contributing_entrants": null, "distinct_rated_opponents": 218, "draws": 185, "entry_count": 8, "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 }, "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": "2026-07-27T11:44:47Z", "losses": 121, "max_score": 51.6075528075571, "measured_at": null, "min_score": 30.140455882095676, "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 438, "rating_method": "sequential_elo", "raw_elo": 1494.876673320847, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 41.99986875925433, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 132 }, { "admitted_plugins": 15, "attempted_matches": 490, "capped_draws": 80, "codegen_cost_usd": { "admitted_cell_count": 15, "cell_count": 8, "cost_basis_counts": { "provider_reported": 32 }, "evidence_basis": "Provider-reported", "failed_cell_count": 1, "max": 0.3926418, "mean": 0.31750829999999997, "median": 0.32150055, "min": 0.2298153, "recorded_attempt_count": 32, "run_count": 16, "total": 5.0801327999999994 }, "codegen_evaluated_cells": 16, "conditional_success_score": 42.25836257311796, "contributing_entrants": null, "distinct_rated_opponents": 245, "draws": 349, "entry_count": 25, "failed_game_aliases": [ "GB2-05" ], "first_pass_admitted": 1, "first_pass_rate": 0.0625, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:44:47Z", "losses": 201, "max_score": 67.21194886050958, "measured_at": null, "min_score": 20.580987520067197, "model_code_failure_rate": 0.0625, "model_code_failures": 1, "model_display_name": "Kimi K3", "model_slug": "moonshotai-kimi-k3", "plugin_success_rate": 0.9375, "provider": "Moonshot", "provider_key": "moonshotai", "rank": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 490, "rating_method": "sequential_elo", "raw_elo": 1525.4769490451797, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "balanced", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 14, "repaired_rate": 0.875, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 41.58201053424288, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 245 }, { "admitted_plugins": 7, "attempted_matches": 402, "capped_draws": 65, "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": 0.21477375, "mean": 0.17756265624999998, "median": 0.17285124999999998, "min": 0.1418975, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 1.42050125 }, "codegen_evaluated_cells": 8, "conditional_success_score": 42.75066336563581, "contributing_entrants": null, "distinct_rated_opponents": 201, "draws": 136, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:44:47Z", "losses": 135, "max_score": 57.44029280728862, "measured_at": null, "min_score": 27.25028757645839, "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": 37, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 402, "rating_method": "sequential_elo", "raw_elo": 1488.849954910172, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 41.34708256937608, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 131 }, { "admitted_plugins": 15, "attempted_matches": 954, "capped_draws": 144, "codegen_cost_usd": { "admitted_cell_count": 15, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 25 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 2, "max": 0.38568888333333334, "mean": 0.29249454166666666, "median": 0.2834616125, "min": 0.2238526, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 25 }, "run_count": 17, "token_priced_attempt_count": 25, "total": 5.07700365 }, "codegen_evaluated_cells": 17, "conditional_success_score": 42.56690883616381, "contributing_entrants": null, "distinct_rated_opponents": 477, "draws": 316, "entry_count": 15, "failed_game_aliases": [ "GB2-02", "GB2-03" ], "first_pass_admitted": 10, "first_pass_rate": 0.5882352941176471, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [ "GB2-01", "GB2-03", "GB2-04", "GB2-05", "GB2-06", "GB2-07" ], "infra_failures_excluded": 9, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:47:56Z", "losses": 336, "max_score": 42.56690883616381, "measured_at": null, "min_score": 42.56690883616381, "model_code_failure_rate": 0.1176470588235294, "model_code_failures": 2, "model_display_name": "GPT-5.4 Nano", "model_slug": "gpt-5-4-nano", "plugin_success_rate": 0.8823529411764706, "provider": "OpenAI", "provider_key": "openai", "rank": 38, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 953, "rating_method": "sequential_elo", "raw_elo": 1505.1823030253686, "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-nano", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 5, "repaired_rate": 0.29411764705882354, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 41.25558005932039, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 1, "wins": 301 }, { "admitted_plugins": 17, "attempted_matches": 1006, "capped_draws": 150, "codegen_cost_usd": { "admitted_cell_count": 17, "cell_count": 8, "cost_basis_counts": { "provider_reported": 35 }, "evidence_basis": "Provider-reported", "failed_cell_count": 7, "max": 0.004834030033333333, "mean": 0.0027724950333333333, "median": 0.002243999216666667, "min": 0.0016912200000000002, "recorded_attempt_count": 35, "run_count": 24, "total": 0.0665398808 }, "codegen_evaluated_cells": 24, "conditional_success_score": 44.944277213825984, "contributing_entrants": null, "distinct_rated_opponents": 503, "draws": 312, "entry_count": 17, "failed_game_aliases": [ "GB2-02", "GB2-03", "GB2-04", "GB2-07", "GB2-08" ], "first_pass_admitted": 12, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:54:00Z", "losses": 372, "max_score": 47.554841215429576, "measured_at": null, "min_score": 39.84236148945967, "model_code_failure_rate": 0.2916666666666667, "model_code_failures": 7, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": 0.7083333333333334, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 39, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1006, "rating_method": "sequential_elo", "raw_elo": 1465.3963149523474, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 5, "repaired_rate": 0.20833333333333337, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 41.23194486637451, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 6, "attempted_matches": 366, "capped_draws": 45, "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": 0.03731, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 0.390976 }, "codegen_evaluated_cells": 8, "conditional_success_score": 43.922090004004865, "contributing_entrants": null, "distinct_rated_opponents": 183, "draws": 99, "entry_count": 6, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:44Z", "losses": 132, "max_score": 56.714061176471255, "measured_at": null, "min_score": 27.89874606250913, "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": 40, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 366, "rating_method": "sequential_elo", "raw_elo": 1502.139772568575, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 40.87411037964668, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 7, "attempted_matches": 412, "capped_draws": 97, "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-2026-07-25": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 1.13802 }, "codegen_evaluated_cells": 8, "conditional_success_score": 41.835071106564946, "contributing_entrants": null, "distinct_rated_opponents": 206, "draws": 222, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:24:42Z", "losses": 92, "max_score": 54.40691412278813, "measured_at": null, "min_score": 27.82065391961682, "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": 41, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 412, "rating_method": "sequential_elo", "raw_elo": 1500.5570908453833, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 40.461550842958125, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 98 }, { "admitted_plugins": 7, "attempted_matches": 216, "capped_draws": 27, "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": 0.121855, "mean": 0.09110296875, "median": 0.09280125, "min": 0.0343775, "recorded_attempt_count": 15, "run_count": 8, "total": 0.7288237499999999 }, "codegen_evaluated_cells": 8, "conditional_success_score": 41.59858019912202, "contributing_entrants": null, "distinct_rated_opponents": 108, "draws": 156, "entry_count": 14, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:36:38Z", "losses": 136, "max_score": 67.56797718896486, "measured_at": null, "min_score": 28.574021625817625, "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": 42, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 216, "rating_method": "sequential_elo", "raw_elo": 1516.4342901702864, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 40.23282435529362, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 6, "attempted_matches": 168, "capped_draws": 27, "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": 0.0276132876, "recorded_attempt_count": 17, "run_count": 8, "total": 1.0777302952 }, "codegen_evaluated_cells": 8, "conditional_success_score": 42.76582870039201, "contributing_entrants": null, "distinct_rated_opponents": 84, "draws": 84, "entry_count": 11, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:51Z", "losses": 154, "max_score": 61.09711900072354, "measured_at": null, "min_score": 25.71921399965224, "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": 43, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 168, "rating_method": "sequential_elo", "raw_elo": 1505.7383432287304, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 39.798087992112826, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 136 }, { "admitted_plugins": 6, "attempted_matches": 374, "capped_draws": 28, "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": 40.96023532559226, "contributing_entrants": null, "distinct_rated_opponents": 187, "draws": 108, "entry_count": 6, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:36:23Z", "losses": 142, "max_score": 65.31899895038302, "measured_at": null, "min_score": 26.62036218416104, "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": 44, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 374, "rating_method": "sequential_elo", "raw_elo": 1466.500794270336, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.2857142857142857, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 39.41175239691446, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 124 }, { "admitted_plugins": 23, "attempted_matches": 1315, "capped_draws": 172, "codegen_cost_usd": { "admitted_cell_count": 23, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 26 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 1, "max": 0.29749325000000004, "mean": 0.24155631250000004, "median": 0.24021375, "min": 0.17873725, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 26 }, "run_count": 24, "token_priced_attempt_count": 26, "total": 5.7973515 }, "codegen_evaluated_cells": 24, "conditional_success_score": 39.63048604415998, "contributing_entrants": null, "distinct_rated_opponents": 658, "draws": 485, "entry_count": 23, "failed_game_aliases": [ "GB2-06" ], "first_pass_admitted": 22, "first_pass_rate": 0.9166666666666666, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:44:52Z", "losses": 433, "max_score": 48.172020366997366, "measured_at": null, "min_score": 27.50563948445921, "model_code_failure_rate": 0.041666666666666664, "model_code_failures": 1, "model_display_name": "GPT-5.4 Mini", "model_slug": "gpt-5-4-mini", "plugin_success_rate": 0.9583333333333334, "provider": "OpenAI", "provider_key": "openai", "rank": 45, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1315, "rating_method": "sequential_elo", "raw_elo": 1489.1305502122211, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.041666666666666664, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 39.21105679311512, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 397 }, { "admitted_plugins": 15, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 15, "cell_count": 8, "cost_basis_counts": { "provider_reported": 23 }, "evidence_basis": "Provider-reported", "failed_cell_count": 1, "max": 0.0148808, "mean": 0.0114004875, "median": 0.01124825, "min": 0.00845595, "recorded_attempt_count": 23, "run_count": 16, "total": 0.1824078 }, "codegen_evaluated_cells": 16, "conditional_success_score": 39.84087462021133, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": 228, "entry_count": 15, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-26T05:18:59Z", "losses": 202, "max_score": 66.08096329718745, "measured_at": null, "min_score": 13.059186845663168, "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": 46, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1497.7232311729522, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Minimal", "reasoning_bracket": "baseline", "reasoning_bucket": "minimal", "reasoning_bucket_label": "Minimal", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "minimal" }, "repaired_admitted": 6, "repaired_rate": 0.375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 39.203214873378464, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 189 }, { "admitted_plugins": 16, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 16, "cell_count": 8, "cost_basis_counts": { "provider_reported": 20 }, "evidence_basis": "Provider-reported", "max": 0.058529250000000005, "mean": 0.03888066562499999, "median": 0.038104875, "min": 0.029012250000000003, "recorded_attempt_count": 20, "run_count": 16, "total": 0.62209065 }, "codegen_evaluated_cells": 16, "conditional_success_score": 38.61863644188435, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": 272, "entry_count": 16, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-26T05:19:02Z", "losses": 208, "max_score": 59.08661445196189, "measured_at": null, "min_score": 24.212894203087245, "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": 47, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1481.401179542269, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Minimal", "reasoning_bracket": "baseline", "reasoning_bucket": "minimal", "reasoning_bucket_label": "Minimal", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "minimal" }, "repaired_admitted": 4, "repaired_rate": 0.25, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 38.61863644188435, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 180 }, { "admitted_plugins": 6, "attempted_matches": 200, "capped_draws": 25, "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": 0.4890770625000001, "median": 0.483741, "min": 0.401826, "recorded_attempt_count": 18, "run_count": 8, "total": 3.912616499999999 }, "codegen_evaluated_cells": 8, "conditional_success_score": 41.30954240884414, "contributing_entrants": null, "distinct_rated_opponents": 100, "draws": 113, "entry_count": 12, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:53:34Z", "losses": 130, "max_score": 66.37931618441283, "measured_at": null, "min_score": 18.44050863736999, "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": 48, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 200, "rating_method": "sequential_elo", "raw_elo": 1511.5059865373096, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 38.442860892954606, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 121 }, { "admitted_plugins": 7, "attempted_matches": 430, "capped_draws": 84, "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": 0.015562441375, "median": 0.0131167185, "min": 0.005612805, "recorded_attempt_count": 12, "run_count": 8, "total": 0.124499531 }, "codegen_evaluated_cells": 8, "conditional_success_score": 39.69653399014509, "contributing_entrants": null, "distinct_rated_opponents": 214, "draws": 152, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": 141, "max_score": 74.39181497022835, "measured_at": null, "min_score": 21.132140682151817, "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": 49, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 430, "rating_method": "sequential_elo", "raw_elo": 1471.0109295011357, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 38.39322572776556, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 7, "attempted_matches": 416, "capped_draws": 52, "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": 0.132112, "mean": 0.0780535, "median": 0.06797, "min": 0.05673, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 0.624428 }, "codegen_evaluated_cells": 8, "conditional_success_score": 39.48455480226403, "contributing_entrants": null, "distinct_rated_opponents": 208, "draws": 137, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:58Z", "losses": 134, "max_score": 50.00396058789727, "measured_at": null, "min_score": 27.396699029090957, "model_code_failure_rate": 0.125, "model_code_failures": 1, "model_display_name": "Claude Sonnet 5", "model_slug": "claude-sonnet-5", "plugin_success_rate": 0.875, "provider": "Anthropic", "provider_key": "anthropic", "rank": 50, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 416, "rating_method": "sequential_elo", "raw_elo": 1480.0737582799902, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 38.18820619603701, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 145 }, { "admitted_plugins": 19, "attempted_matches": 1197, "capped_draws": 164, "codegen_cost_usd": { "admitted_cell_count": 19, "cell_count": 8, "cost_basis_counts": { "provider_reported": 57 }, "evidence_basis": "Provider-reported", "failed_cell_count": 8, "max": 0.25293804044999996, "mean": 0.19953128278325, "median": 0.20662718916666667, "min": 0.13279406625, "recorded_attempt_count": 57, "run_count": 27, "total": 5.24138213703 }, "codegen_evaluated_cells": 27, "conditional_success_score": 41.66158464393463, "contributing_entrants": null, "distinct_rated_opponents": 599, "draws": 428, "entry_count": 19, "failed_game_aliases": [ "GB2-01", "GB2-03", "GB2-04", "GB2-06" ], "first_pass_admitted": 1, "first_pass_rate": 0.037037037037037035, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [ "GB2-03", "GB2-06" ], "infra_failures_excluded": 2, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:55:02Z", "losses": 392, "max_score": 57.37331813393658, "measured_at": null, "min_score": 30.05739733199343, "model_code_failure_rate": 0.2962962962962963, "model_code_failures": 8, "model_display_name": "GLM-5.2", "model_slug": "z-ai-glm-5-2", "plugin_success_rate": 0.7037037037037037, "provider": "Zhipu", "provider_key": "z-ai", "rank": 51, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1197, "rating_method": "sequential_elo", "raw_elo": 1516.1537157939886, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 18, "repaired_rate": 0.6666666666666666, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 38.15779267423163, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 6, "attempted_matches": 220, "capped_draws": 32, "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": 40.879144070193625, "contributing_entrants": null, "distinct_rated_opponents": 110, "draws": 140, "entry_count": 12, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:36:31Z", "losses": 122, "max_score": 58.39911627396981, "measured_at": null, "min_score": 27.02024765518864, "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": 52, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 220, "rating_method": "sequential_elo", "raw_elo": 1500.1500481014182, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 38.042330107656966, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 372, "capped_draws": 22, "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": 40.77789385607518, "contributing_entrants": null, "distinct_rated_opponents": 186, "draws": 97, "entry_count": 6, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:30:08Z", "losses": 135, "max_score": 52.69666989897096, "measured_at": null, "min_score": 27.899111953447644, "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": 53, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 372, "rating_method": "sequential_elo", "raw_elo": 1484.0635842495656, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 37.94810616641322, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 16, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 16, "cell_count": 8, "cost_basis_counts": { "provider_reported": 34 }, "evidence_basis": "Provider-reported", "max": 0.04815395, "mean": 0.0408814375, "median": 0.040641, "min": 0.0341807, "recorded_attempt_count": 34, "run_count": 16, "total": 0.654103 }, "codegen_evaluated_cells": 16, "conditional_success_score": 37.08427156622473, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": 232, "entry_count": 16, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-26T04:34:09Z", "losses": 230, "max_score": 53.91719217050105, "measured_at": null, "min_score": 25.25796091549614, "model_code_failure_rate": 0.0, "model_code_failures": 0, "model_display_name": "Gemini 3.5 Flash Lite", "model_slug": "google-gemini-3-5-flash-lite", "plugin_success_rate": 1.0, "provider": "Google", "provider_key": "google", "rank": 54, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1468.5191981065773, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 16, "repaired_rate": 1.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 37.08427156622473, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 12, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 12, "cell_count": 8, "cost_basis_counts": { "provider_reported": 32 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.04649778, "mean": 0.039593841, "median": 0.039509778, "min": 0.030762138, "recorded_attempt_count": 32, "run_count": 16, "total": 0.6335014560000001 }, "codegen_evaluated_cells": 16, "conditional_success_score": 39.55776475771556, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": 126, "entry_count": 12, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-26T05:11:55Z", "losses": 198, "max_score": 51.35463436894605, "measured_at": null, "min_score": 19.697931844478177, "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": 55, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1455.471148029714, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 12, "repaired_rate": 0.75, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 36.812648098747886, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 162 }, { "admitted_plugins": 8, "attempted_matches": 276, "capped_draws": 22, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 13 }, "evidence_basis": "Standard list-price estimate", "max": 0.136952, "mean": 0.07424775, "median": 0.070604, "min": 0.041758, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 13 }, "run_count": 8, "token_priced_attempt_count": 13, "total": 0.593982 }, "codegen_evaluated_cells": 8, "conditional_success_score": 36.72182476113313, "contributing_entrants": null, "distinct_rated_opponents": 137, "draws": 87, "entry_count": 12, "failed_game_aliases": [], "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": 92, "max_score": 83.5076304126712, "measured_at": null, "min_score": 17.83316943117343, "model_code_failure_rate": 0.0, "model_code_failures": 0, "model_display_name": "O3", "model_slug": "o3", "plugin_success_rate": 1.0, "provider": "OpenAI", "provider_key": "openai", "rank": 56, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 276, "rating_method": "sequential_elo", "raw_elo": 1515.2721863391596, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": 4, "repaired_rate": 0.5, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 36.72182476113313, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 111 }, { "admitted_plugins": 8, "attempted_matches": 246, "capped_draws": 30, "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": 0.4852845999999999 }, "codegen_evaluated_cells": 8, "conditional_success_score": 36.60929744604539, "contributing_entrants": null, "distinct_rated_opponents": 123, "draws": 178, "entry_count": 16, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:48:47Z", "losses": 161, "max_score": 53.83120272886001, "measured_at": null, "min_score": 26.493587534338452, "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": 57, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 246, "rating_method": "sequential_elo", "raw_elo": 1479.0876467501992, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 8, "repaired_rate": 1.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 36.60929744604539, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 151 }, { "admitted_plugins": 8, "attempted_matches": 614, "capped_draws": 43, "codegen_cost_usd": null, "codegen_evaluated_cells": 8, "conditional_success_score": 36.3327658288794, "contributing_entrants": null, "distinct_rated_opponents": 307, "draws": 416, "entry_count": 39, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:53:12Z", "losses": 498, "max_score": 48.67604159099529, "measured_at": null, "min_score": 21.218380859420797, "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": 58, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 614, "rating_method": "sequential_elo", "raw_elo": 1487.3185279071783, "reasoning_level": "Extended thinking (legacy shared budget)", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_exact", "request_mode": "effort", "requested_effort": "legacy_shared_thinking_budget", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Extended thinking (legacy shared budget)", "reasoning_bracket": "intensive", "reasoning_bucket": "legacy_shared_thinking_budget", "reasoning_bucket_label": "Extended thinking (legacy shared budget)", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "legacy_shared_thinking_budget" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 36.3327658288794, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 402 }, { "admitted_plugins": 6, "attempted_matches": 404, "capped_draws": 80, "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": 38.897398778071, "contributing_entrants": null, "distinct_rated_opponents": 202, "draws": 193, "entry_count": 6, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:48:11Z", "losses": 108, "max_score": 71.25680984831166, "measured_at": null, "min_score": 26.336139967911993, "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": 404, "rating_method": "sequential_elo", "raw_elo": 1487.264677108794, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 36.19810830930494, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 103 }, { "admitted_plugins": 7, "attempted_matches": 274, "capped_draws": 47, "codegen_cost_usd": { "admitted_cell_count": 7, "cell_count": 8, "cost_basis_counts": { "provider_reported": 20 }, "evidence_basis": "Provider-reported", "failed_cell_count": 1, "max": 0.03772852, "mean": 0.024905897500000003, "median": 0.0260953, "min": 0.00984735, "recorded_attempt_count": 20, "run_count": 8, "total": 0.19924718 }, "codegen_evaluated_cells": 8, "conditional_success_score": 37.07527376145696, "contributing_entrants": null, "distinct_rated_opponents": 137, "draws": 75, "entry_count": 7, "failed_game_aliases": [ "GB2-02" ], "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:44:14Z", "losses": 112, "max_score": 48.91915370704513, "measured_at": null, "min_score": 19.24313559757037, "model_code_failure_rate": 0.125, "model_code_failures": 1, "model_display_name": "Step 3.7 Flash", "model_slug": "stepfun-step-3-7-flash", "plugin_success_rate": 0.875, "provider": "StepFun", "provider_key": "stepfun", "rank": 60, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 274, "rating_method": "sequential_elo", "raw_elo": 1457.3245219395228, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 35.858026164090255, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 6, "attempted_matches": 180, "capped_draws": 2, "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": 37.9674466886763, "contributing_entrants": null, "distinct_rated_opponents": 90, "draws": 95, "entry_count": 12, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:03:48Z", "losses": 139, "max_score": 47.67871891237462, "measured_at": null, "min_score": 24.01242101325399, "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": 61, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 180, "rating_method": "sequential_elo", "raw_elo": 1505.934469262074, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 35.33269037618208, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 128 }, { "admitted_plugins": 14, "attempted_matches": 892, "capped_draws": 158, "codegen_cost_usd": { "admitted_cell_count": 14, "cell_count": 8, "cost_basis_counts": { "provider_reported": 25 }, "evidence_basis": "Provider-reported", "failed_cell_count": 2, "max": 0.014209038, "mean": 0.0093957345, "median": 0.009312405, "min": 0.004429524000000001, "recorded_attempt_count": 25, "run_count": 16, "total": 0.150331752 }, "codegen_evaluated_cells": 16, "conditional_success_score": 36.52896680779845, "contributing_entrants": null, "distinct_rated_opponents": 446, "draws": 307, "entry_count": 14, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:54:00Z", "losses": 338, "max_score": 52.38713921457689, "measured_at": null, "min_score": 21.811735212142757, "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": 62, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 892, "rating_method": "sequential_elo", "raw_elo": 1452.8076610451176, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 6, "repaired_rate": 0.375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 35.32965544553668, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 247 }, { "admitted_plugins": 11, "attempted_matches": 694, "capped_draws": 78, "codegen_cost_usd": { "admitted_cell_count": 11, "cell_count": 8, "cost_basis_counts": { "provider_reported": 26 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.015971877, "mean": 0.00979196948, "median": 0.009500477, "min": 0.003562685, "recorded_attempt_count": 26, "run_count": 15, "total": 0.14255357568000002 }, "codegen_evaluated_cells": 15, "conditional_success_score": 37.57837372308959, "contributing_entrants": null, "distinct_rated_opponents": 347, "draws": 182, "entry_count": 11, "failed_game_aliases": [ "GB2-03", "GB2-04" ], "first_pass_admitted": 5, "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 }, "infra_excluded_game_aliases": [ "GB2-08" ], "infra_failures_excluded": 1, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:53:45Z", "losses": 310, "max_score": 49.87227457080003, "measured_at": null, "min_score": 30.214944656619977, "model_code_failure_rate": 0.26666666666666666, "model_code_failures": 4, "model_display_name": "DeepSeek V4 Flash", "model_slug": "deepseek-deepseek-v4-flash", "plugin_success_rate": 0.7333333333333333, "provider": "DeepSeek", "provider_key": "deepseek", "rank": 63, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 694, "rating_method": "sequential_elo", "raw_elo": 1439.838020168251, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 6, "repaired_rate": 0.4, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 34.77469565398564, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 16, "attempted_matches": 936, "capped_draws": 90, "codegen_cost_usd": { "admitted_cell_count": 16, "cell_count": 8, "cost_basis_counts": { "provider_reported": 32 }, "evidence_basis": "Provider-reported", "max": 0.03261155, "mean": 0.02559155625, "median": 0.02516155, "min": 0.017927, "recorded_attempt_count": 32, "run_count": 16, "total": 0.4094649 }, "codegen_evaluated_cells": 16, "conditional_success_score": 34.578316108190634, "contributing_entrants": null, "distinct_rated_opponents": 466, "draws": 344, "entry_count": 15, "failed_game_aliases": [], "first_pass_admitted": 1, "first_pass_rate": 0.0625, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:31:38Z", "losses": 331, "max_score": 49.78746785854181, "measured_at": null, "min_score": 17.279603403559378, "model_code_failure_rate": 0.0, "model_code_failures": 0, "model_display_name": "Gemini 3.5 Flash Lite", "model_slug": "google-gemini-3-5-flash-lite", "plugin_success_rate": 1.0, "provider": "Google", "provider_key": "google", "rank": 64, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 930, "rating_method": "sequential_elo", "raw_elo": 1434.0689168288116, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 15, "repaired_rate": 0.9375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 34.578316108190634, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 255 }, { "admitted_plugins": 12, "attempted_matches": 736, "capped_draws": 70, "codegen_cost_usd": { "admitted_cell_count": 12, "cell_count": 8, "cost_basis_counts": { "provider_reported": 28 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.053540475, "mean": 0.026315053125, "median": 0.024512850000000003, "min": 0.012912625, "recorded_attempt_count": 28, "run_count": 16, "total": 0.42104085 }, "codegen_evaluated_cells": 16, "conditional_success_score": 36.551991647127046, "contributing_entrants": null, "distinct_rated_opponents": 368, "draws": 247, "entry_count": 12, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:37:44Z", "losses": 303, "max_score": 49.94247004323288, "measured_at": null, "min_score": 26.11987489541008, "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": 65, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 736, "rating_method": "sequential_elo", "raw_elo": 1461.4945458521415, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 5, "repaired_rate": 0.3125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 34.01546103667579, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 186 }, { "admitted_plugins": 24, "attempted_matches": 1432, "capped_draws": 196, "codegen_cost_usd": { "admitted_cell_count": 24, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 29 }, "evidence_basis": "Standard list-price estimate", "max": 0.021615250000000003, "mean": 0.017288937500000004, "median": 0.01830825, "min": 0.01259225, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 29 }, "run_count": 24, "token_priced_attempt_count": 29, "total": 0.4149345 }, "codegen_evaluated_cells": 24, "conditional_success_score": 33.58863538792332, "contributing_entrants": null, "distinct_rated_opponents": 715, "draws": 588, "entry_count": 24, "failed_game_aliases": [], "first_pass_admitted": 19, "first_pass_rate": 0.7916666666666666, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": 496, "max_score": 49.45153806809078, "measured_at": null, "min_score": 21.382657975617843, "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": 66, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1432, "rating_method": "sequential_elo", "raw_elo": 1427.5369329615808, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 5, "repaired_rate": 0.20833333333333337, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 33.58863538792332, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 348 }, { "admitted_plugins": 11, "attempted_matches": 698, "capped_draws": 33, "codegen_cost_usd": { "admitted_cell_count": 11, "cell_count": 8, "cost_basis_counts": { "provider_reported": 37 }, "evidence_basis": "Provider-reported", "failed_cell_count": 5, "max": 0.07934969, "mean": 0.053583788125, "median": 0.0553142075, "min": 0.02549349, "recorded_attempt_count": 37, "run_count": 16, "total": 0.85734061 }, "codegen_evaluated_cells": 16, "conditional_success_score": 36.467283143076706, "contributing_entrants": null, "distinct_rated_opponents": 349, "draws": 183, "entry_count": 11, "failed_game_aliases": [ "GB2-02", "GB2-03", "GB2-06", "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:31:22Z", "losses": 285, "max_score": 53.3592866591907, "measured_at": null, "min_score": 29.420591696289264, "model_code_failure_rate": 0.3125, "model_code_failures": 5, "model_display_name": "Inkling", "model_slug": "thinkingmachines-inkling", "plugin_success_rate": 0.6875, "provider": "Other", "provider_key": "other", "rank": 67, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 698, "rating_method": "sequential_elo", "raw_elo": 1456.6485324874122, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 11, "repaired_rate": 0.6875, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 33.20638391452173, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 230 }, { "admitted_plugins": 7, "attempted_matches": 368, "capped_draws": 67, "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": 0.001130258, "recorded_attempt_count": 16, "run_count": 8, "total": 0.01972526 }, "codegen_evaluated_cells": 8, "conditional_success_score": 33.28749406524547, "contributing_entrants": null, "distinct_rated_opponents": 184, "draws": 173, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:44:30Z", "losses": 112, "max_score": 38.85920360288856, "measured_at": null, "min_score": 28.976047880768927, "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": 68, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 368, "rating_method": "sequential_elo", "raw_elo": 1440.504410376032, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 32.1946060549241, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 83 }, { "admitted_plugins": 8, "attempted_matches": 288, "capped_draws": 41, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "provider_reported": 13 }, "evidence_basis": "Provider-reported", "max": 0.0032939400000000004, "mean": 0.0016413085, "median": 0.0014119655, "min": 0.00045831, "recorded_attempt_count": 13, "run_count": 8, "total": 0.013130468 }, "codegen_evaluated_cells": 8, "conditional_success_score": 31.740856996211672, "contributing_entrants": null, "distinct_rated_opponents": 144, "draws": 113, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:32Z", "losses": 106, "max_score": 47.15146009630666, "measured_at": null, "min_score": 14.420068188974202, "model_code_failure_rate": 0.0, "model_code_failures": 0, "model_display_name": "GPT-OSS 120B", "model_slug": "openai-gpt-oss-120b", "plugin_success_rate": 1.0, "provider": "OpenAI", "provider_key": "openai", "rank": 69, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 288, "rating_method": "sequential_elo", "raw_elo": 1438.9374320645486, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 31.740856996211672, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 69 }, { "admitted_plugins": 11, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 11, "cell_count": 8, "cost_basis_counts": { "provider_reported": 22 }, "evidence_basis": "Provider-reported", "failed_cell_count": 3, "max": 0.00596013, "mean": 0.0023956312500000004, "median": 0.00186283, "min": 0.00105702, "recorded_attempt_count": 22, "run_count": 14, "total": 0.03542156 }, "codegen_evaluated_cells": 14, "conditional_success_score": 33.49075006569608, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": 223, "entry_count": 11, "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 }, "infra_excluded_game_aliases": [ "GB2-04", "GB2-06" ], "infra_failures_excluded": 2, "is_recent_addition": false, "last_measured_at": "2026-07-26T04:30:24Z", "losses": 140, "max_score": 40.298818357212, "measured_at": null, "min_score": 26.335060663959837, "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": 70, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1451.4196186479696, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 4, "repaired_rate": 0.2857142857142857, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 31.531239011473826, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 93 }, { "admitted_plugins": 4, "attempted_matches": 130, "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": 36.230230619845194, "contributing_entrants": null, "distinct_rated_opponents": 65, "draws": 47, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [ "GB2-01" ], "infra_failures_excluded": 1, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:05:52Z", "losses": 108, "max_score": 43.06115710405442, "measured_at": null, "min_score": 29.15567824497275, "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": 71, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 130, "rating_method": "sequential_elo", "raw_elo": 1456.4764198441117, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 4, "repaired_rate": 0.5714285714285714, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 31.500074891654457, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 83 }, { "admitted_plugins": 25, "attempted_matches": 1484, "capped_draws": 148, "codegen_cost_usd": { "admitted_cell_count": 25, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 49 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 7, "max": 0.036200562500000005, "mean": 0.024352715625, "median": 0.02520601875, "min": 0.0165820625, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 49 }, "run_count": 32, "token_priced_attempt_count": 49, "total": 0.7792869 }, "codegen_evaluated_cells": 32, "conditional_success_score": 33.32297233861824, "contributing_entrants": null, "distinct_rated_opponents": 743, "draws": 411, "entry_count": 25, "failed_game_aliases": [ "GB2-02", "GB2-03", "GB2-04", "GB2-08" ], "first_pass_admitted": 13, "first_pass_rate": 0.40625, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:44:47Z", "losses": 669, "max_score": 54.484864054652334, "measured_at": null, "min_score": 19.139574631625756, "model_code_failure_rate": 0.21875, "model_code_failures": 7, "model_display_name": "GPT-5.4 Nano", "model_slug": "gpt-5-4-nano", "plugin_success_rate": 0.78125, "provider": "OpenAI", "provider_key": "openai", "rank": 72, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1484, "rating_method": "sequential_elo", "raw_elo": 1435.8363111239446, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 12, "repaired_rate": 0.375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 31.32861821186002, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 404 }, { "admitted_plugins": 6, "attempted_matches": 334, "capped_draws": 59, "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": 32.157004896285834, "contributing_entrants": null, "distinct_rated_opponents": 167, "draws": 100, "entry_count": 6, "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 }, "infra_excluded_game_aliases": [ "GB2-02" ], "infra_failures_excluded": 1, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:24:44Z", "losses": 137, "max_score": 44.68186759149837, "measured_at": null, "min_score": 21.93738491295836, "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": 73, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 334, "rating_method": "sequential_elo", "raw_elo": 1410.5889455812448, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 1, "repaired_rate": 0.14285714285714285, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 30.941324060385092, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 97 }, { "admitted_plugins": 19, "attempted_matches": 1138, "capped_draws": 180, "codegen_cost_usd": { "admitted_cell_count": 19, "cell_count": 8, "cost_basis_counts": { "provider_reported": 34 }, "evidence_basis": "Provider-reported", "failed_cell_count": 5, "max": 0.0027823742, "mean": 0.0022230800541666665, "median": 0.002112839, "min": 0.001825724, "recorded_attempt_count": 34, "run_count": 24, "total": 0.0533539213 }, "codegen_evaluated_cells": 24, "conditional_success_score": 32.397303698325416, "contributing_entrants": null, "distinct_rated_opponents": 569, "draws": 471, "entry_count": 19, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-06" ], "first_pass_admitted": 14, "first_pass_rate": 0.5833333333333334, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": 407, "max_score": 38.6894460221831, "measured_at": null, "min_score": 26.61960427875735, "model_code_failure_rate": 0.20833333333333337, "model_code_failures": 5, "model_display_name": "DeepSeek V4 Flash", "model_slug": "deepseek-deepseek-v4-flash", "plugin_success_rate": 0.7916666666666666, "provider": "DeepSeek", "provider_key": "deepseek", "rank": 74, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1138, "rating_method": "sequential_elo", "raw_elo": 1436.513869453124, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 5, "repaired_rate": 0.20833333333333337, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 30.559374230943043, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 260 }, { "admitted_plugins": 25, "attempted_matches": 1504, "capped_draws": 249, "codegen_cost_usd": { "admitted_cell_count": 25, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 56 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 7, "max": 0.013223525, "mean": 0.0089983359375, "median": 0.00845865, "min": 0.0058062875, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 56 }, "run_count": 32, "token_priced_attempt_count": 56, "total": 0.28794675000000003 }, "codegen_evaluated_cells": 32, "conditional_success_score": 32.37514569421184, "contributing_entrants": null, "distinct_rated_opponents": 752, "draws": 593, "entry_count": 25, "failed_game_aliases": [ "GB2-03", "GB2-04", "GB2-05", "GB2-06", "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": 536, "max_score": 36.489269004581146, "measured_at": null, "min_score": 28.309344060133164, "model_code_failure_rate": 0.21875, "model_code_failures": 7, "model_display_name": "GPT-5.4 Nano", "model_slug": "gpt-5-4-nano", "plugin_success_rate": 0.78125, "provider": "OpenAI", "provider_key": "openai", "rank": 75, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1504, "rating_method": "sequential_elo", "raw_elo": 1446.818247883918, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 15, "repaired_rate": 0.46875, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 30.43751825919392, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 375 }, { "admitted_plugins": 6, "attempted_matches": 176, "capped_draws": 25, "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": 32.26358588454963, "contributing_entrants": null, "distinct_rated_opponents": 88, "draws": 110, "entry_count": 12, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:47Z", "losses": 142, "max_score": 42.997436567986185, "measured_at": null, "min_score": 19.858838132294075, "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": 76, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1443.823114057231, "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": "other", "provider_model": "cohere/north-mini-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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 30.02464979621979, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 98 }, { "admitted_plugins": 5, "attempted_matches": 202, "capped_draws": 32, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 18 }, "evidence_basis": "Provider-reported", "failed_cell_count": 3, "max": 0.01660212, "mean": 0.00855959175, "median": 0.005979701, "min": 0.00271606, "recorded_attempt_count": 18, "run_count": 8, "total": 0.068476734 }, "codegen_evaluated_cells": 8, "conditional_success_score": 33.62820028985485, "contributing_entrants": null, "distinct_rated_opponents": 101, "draws": 150, "entry_count": 10, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:46:17Z", "losses": 104, "max_score": 60.76783956869306, "measured_at": null, "min_score": 19.179163036226186, "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": 77, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 202, "rating_method": "sequential_elo", "raw_elo": 1476.6748561574834, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 29.900168086056908, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 5, "attempted_matches": 298, "capped_draws": 56, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 19 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.0445032, "mean": 0.03204184375, "median": 0.0312573, "min": 0.0200767, "recorded_attempt_count": 19, "run_count": 9, "total": 0.2854256 }, "codegen_evaluated_cells": 9, "conditional_success_score": 33.72406167819707, "contributing_entrants": null, "distinct_rated_opponents": 149, "draws": 112, "entry_count": 5, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:38Z", "losses": 110, "max_score": 59.81864880409941, "measured_at": null, "min_score": 5.146710224123554, "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": 78, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 298, "rating_method": "sequential_elo", "raw_elo": 1430.6490408549776, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 5, "repaired_rate": 0.5555555555555556, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 29.11533212995305, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 76 }, { "admitted_plugins": 15, "attempted_matches": 476, "capped_draws": 45, "codegen_cost_usd": { "admitted_cell_count": 15, "cell_count": 8, "cost_basis_counts": { "provider_reported": 46 }, "evidence_basis": "Provider-reported", "failed_cell_count": 6, "max": 0.02904086, "mean": 0.020196066154166664, "median": 0.0210709803, "min": 0.0085050301, "recorded_attempt_count": 46, "run_count": 21, "total": 0.426437947 }, "codegen_evaluated_cells": 21, "conditional_success_score": 30.35065853930814, "contributing_entrants": null, "distinct_rated_opponents": 238, "draws": 375, "entry_count": 30, "failed_game_aliases": [ "GB2-01", "GB2-03", "GB2-06", "GB2-08" ], "first_pass_admitted": 1, "first_pass_rate": 0.047619047619047616, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [ "GB2-03", "GB2-06", "GB2-07" ], "infra_failures_excluded": 3, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:44Z", "losses": 313, "max_score": 38.75915984031178, "measured_at": null, "min_score": 25.89649759084934, "model_code_failure_rate": 0.2857142857142857, "model_code_failures": 6, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": 0.7142857142857143, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 79, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 476, "rating_method": "sequential_elo", "raw_elo": 1451.7143963431668, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 14, "repaired_rate": 0.6666666666666666, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 27.902049817221116, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 236 }, { "admitted_plugins": 7, "attempted_matches": 214, "capped_draws": 30, "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": 0.09705768, "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": 28.831135463657088, "contributing_entrants": null, "distinct_rated_opponents": 107, "draws": 157, "entry_count": 14, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:47Z", "losses": 177, "max_score": 44.83748928548472, "measured_at": null, "min_score": 12.243419652002428, "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": 80, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 214, "rating_method": "sequential_elo", "raw_elo": 1421.2178272559431, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 7, "repaired_rate": 0.875, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 27.884557682511353, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 86 }, { "admitted_plugins": 6, "attempted_matches": 344, "capped_draws": 54, "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": 0.0149315, "mean": 0.00915140625, "median": 0.00943475, "min": 0.00402875, "recorded_attempt_count": 16, "run_count": 8, "total": 0.07321125 }, "codegen_evaluated_cells": 8, "conditional_success_score": 29.652763827122897, "contributing_entrants": null, "distinct_rated_opponents": 172, "draws": 90, "entry_count": 6, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:44:43Z", "losses": 154, "max_score": 42.33396509337835, "measured_at": null, "min_score": 5.363284090316728, "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": 81, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 344, "rating_method": "sequential_elo", "raw_elo": 1390.1487813771837, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 4, "repaired_rate": 0.5, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 27.59500610332754, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 100 }, { "admitted_plugins": 6, "attempted_matches": 344, "capped_draws": 18, "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": 30.53831550280331, "contributing_entrants": null, "distinct_rated_opponents": 172, "draws": 100, "entry_count": 6, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:44:24Z", "losses": 152, "max_score": 35.74840773334668, "measured_at": null, "min_score": 18.05367245403799, "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": 82, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 344, "rating_method": "sequential_elo", "raw_elo": 1402.985140004401, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.2222222222222222, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 27.594483075202657, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 7, "attempted_matches": 252, "capped_draws": 13, "codegen_cost_usd": { "admitted_cell_count": 7, "cell_count": 8, "cost_basis_counts": { "provider_reported": 13 }, "evidence_basis": "Provider-reported", "failed_cell_count": 2, "max": 0.0056201515, "mean": 0.0029446039375, "median": 0.001956843, "min": 0.001266762, "recorded_attempt_count": 13, "run_count": 9, "total": 0.029176982999999997 }, "codegen_evaluated_cells": 9, "conditional_success_score": 29.32204005563696, "contributing_entrants": null, "distinct_rated_opponents": 126, "draws": 130, "entry_count": 14, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:37:26Z", "losses": 208, "max_score": 51.729550125281335, "measured_at": null, "min_score": 18.058264435137527, "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": 83, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 252, "rating_method": "sequential_elo", "raw_elo": 1453.3749708580128, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 2, "repaired_rate": 0.2222222222222222, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 27.53645729515707, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 144 }, { "admitted_plugins": 5, "attempted_matches": 188, "capped_draws": 29, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 18 }, "evidence_basis": "Provider-reported", "failed_cell_count": 3, "max": 0.08193244999999999, "mean": 0.05495368125, "median": 0.056941025, "min": 0.02174195, "recorded_attempt_count": 18, "run_count": 8, "total": 0.43962945 }, "codegen_evaluated_cells": 8, "conditional_success_score": 30.663694734085283, "contributing_entrants": null, "distinct_rated_opponents": 94, "draws": 59, "entry_count": 10, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:46:13Z", "losses": 179, "max_score": 40.40736615648161, "measured_at": null, "min_score": 19.617975464814673, "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": 84, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1404.3049647259802, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 27.2643084906714, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 10, "attempted_matches": 604, "capped_draws": 147, "codegen_cost_usd": { "admitted_cell_count": 10, "cell_count": 8, "cost_basis_counts": { "provider_reported": 29 }, "evidence_basis": "Provider-reported", "failed_cell_count": 6, "max": 0.0, "mean": 0.0, "median": 0.0, "min": 0.0, "recorded_attempt_count": 29, "run_count": 16, "total": 0.0 }, "codegen_evaluated_cells": 16, "conditional_success_score": 28.79431096575087, "contributing_entrants": null, "distinct_rated_opponents": 302, "draws": 302, "entry_count": 10, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:48:36Z", "losses": 215, "max_score": 44.131890322774105, "measured_at": null, "min_score": 18.594475422927697, "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": 85, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 604, "rating_method": "sequential_elo", "raw_elo": 1414.0503243261192, "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": true, "evidence_status": "retained_exact", "request_mode": "toggle", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 4, "repaired_rate": 0.25, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 25.602165158326375, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 5, "attempted_matches": 152, "capped_draws": 10, "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": 0.10247140625, "median": 0.113468875, "min": 0.061553, "recorded_attempt_count": 17, "run_count": 8, "total": 0.8197712500000001 }, "codegen_evaluated_cells": 8, "conditional_success_score": 27.98588259282322, "contributing_entrants": null, "distinct_rated_opponents": 76, "draws": 49, "entry_count": 10, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:36:40Z", "losses": 168, "max_score": 40.05712610425944, "measured_at": null, "min_score": 3.452798895447958, "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": 86, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 152, "rating_method": "sequential_elo", "raw_elo": 1394.6530751194732, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 24.88335939329212, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 79 }, { "admitted_plugins": 9, "attempted_matches": 333, "capped_draws": 63, "codegen_cost_usd": { "admitted_cell_count": 9, "cell_count": 8, "cost_basis_counts": { "provider_reported": 33 }, "evidence_basis": "Provider-reported", "failed_cell_count": 7, "max": 0.039679950000000005, "mean": 0.029276065625, "median": 0.0306386, "min": 0.01864685, "recorded_attempt_count": 33, "run_count": 16, "total": 0.46841705 }, "codegen_evaluated_cells": 16, "conditional_success_score": 27.60265191197351, "contributing_entrants": null, "distinct_rated_opponents": 167, "draws": 294, "entry_count": 18, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:37:14Z", "losses": 191, "max_score": 31.89087169341551, "measured_at": null, "min_score": 24.99822893746736, "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": 87, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 333, "rating_method": "sequential_elo", "raw_elo": 1441.7629523084724, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 7, "repaired_rate": 0.4375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 23.904597767588164, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 106 }, { "admitted_plugins": 8, "attempted_matches": 454, "capped_draws": 66, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 9 }, "evidence_basis": "Standard list-price estimate", "max": 0.038815, "mean": 0.02196775, "median": 0.0196975, "min": 0.016152, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 0.17574199999999998 }, "codegen_evaluated_cells": 8, "conditional_success_score": 23.750537922707625, "contributing_entrants": null, "distinct_rated_opponents": 227, "draws": 185, "entry_count": 8, "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 }, "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": "2026-07-27T11:59:32Z", "losses": 206, "max_score": 42.8401440385904, "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": 88, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 453, "rating_method": "sequential_elo", "raw_elo": 1352.506391499512, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 23.750537922707625, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 62 }, { "admitted_plugins": 5, "attempted_matches": 167, "capped_draws": 29, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 18 }, "evidence_basis": "Provider-reported", "failed_cell_count": 3, "max": 0.0422995, "mean": 0.0264053125, "median": 0.022682375, "min": 0.01946775, "recorded_attempt_count": 18, "run_count": 8, "total": 0.2112425 }, "codegen_evaluated_cells": 8, "conditional_success_score": 26.571197548255896, "contributing_entrants": null, "distinct_rated_opponents": 84, "draws": 104, "entry_count": 10, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:53:48Z", "losses": 169, "max_score": 37.38497422902105, "measured_at": null, "min_score": 15.144663326584237, "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": 89, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 167, "rating_method": "sequential_elo", "raw_elo": 1393.3296662380549, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 23.625506750070084, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 62 }, { "admitted_plugins": 8, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "provider_reported": 33 }, "evidence_basis": "Provider-reported", "failed_cell_count": 8, "max": 0.341716425, "mean": 0.30867194062500003, "median": 0.31836633750000004, "min": 0.2745495, "recorded_attempt_count": 33, "run_count": 16, "total": 4.9387510500000005 }, "codegen_evaluated_cells": 16, "conditional_success_score": 62.72324131369825, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": 106, "entry_count": 8, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-26T05:19:08Z", "losses": 59, "max_score": 89.93824120320421, "measured_at": null, "min_score": 35.50824142419229, "model_code_failure_rate": 0.5, "model_code_failures": 8, "model_display_name": "Gemini 3.6 Flash", "model_slug": "google-gemini-3-6-flash", "plugin_success_rate": 0.5, "provider": "Google", "provider_key": "google", "rank": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "provisional", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1608.4207637110949, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 8, "repaired_rate": 0.5, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 52.74374877378255, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 173 }, { "admitted_plugins": 4, "attempted_matches": 158, "capped_draws": 1, "codegen_cost_usd": { "admitted_cell_count": 4, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 8 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 4, "max": 0.055222, "mean": 0.046879, "median": 0.046959, "min": 0.039474, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 0.375032 }, "codegen_evaluated_cells": 8, "conditional_success_score": 52.75022683541799, "contributing_entrants": null, "distinct_rated_opponents": 79, "draws": 12, "entry_count": 8, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "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 }, "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": "2026-07-27T11:37:12Z", "losses": 136, "max_score": 51.26533615379074, "measured_at": null, "min_score": 35.574874573353014, "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": 158, "rating_method": "sequential_elo", "raw_elo": 1502.8155544211063, "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_literal_legacy", "request_mode": "effort", "requested_effort": "high", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 44.35747664972328, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 16, "attempted_matches": 664, "capped_draws": 149, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 332, "draws": 245, "entry_count": 16, "failed_game_aliases": [], "first_pass_admitted": null, "first_pass_rate": null, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:55:02Z", "losses": 192, "max_score": 68.70041680687149, "measured_at": null, "min_score": 24.41934796442663, "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": "provisional", "rated_matches": 664, "rating_method": "sequential_elo", "raw_elo": 1524.646156720068, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 43.93076557633315, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 227 }, { "admitted_plugins": 8, "attempted_matches": 328, "capped_draws": 58, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 164, "draws": 132, "entry_count": 8, "failed_game_aliases": [], "first_pass_admitted": null, "first_pass_rate": null, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:54:22Z", "losses": 98, "max_score": 55.05572388516481, "measured_at": null, "min_score": 26.09668923633087, "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": "provisional", "rated_matches": 328, "rating_method": "sequential_elo", "raw_elo": 1501.062269125725, "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": "omitted", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 41.45827687268098, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 98 }, { "admitted_plugins": 28, "attempted_matches": 1140, "capped_draws": 73, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 570, "draws": 328, "entry_count": 28, "failed_game_aliases": [], "first_pass_admitted": null, "first_pass_rate": null, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:55:02Z", "losses": 420, "max_score": 53.48050971680028, "measured_at": null, "min_score": 26.49126905850573, "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": "provisional", "rated_matches": 1140, "rating_method": "sequential_elo", "raw_elo": 1488.6998716279136, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 39.66616940391225, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 392 }, { "admitted_plugins": 8, "attempted_matches": 332, "capped_draws": 28, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 165, "draws": 100, "entry_count": 8, "failed_game_aliases": [], "first_pass_admitted": null, "first_pass_rate": null, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:48:31Z", "losses": 128, "max_score": 56.67090350467359, "measured_at": null, "min_score": 22.47989431367969, "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": "provisional", "rated_matches": 332, "rating_method": "sequential_elo", "raw_elo": 1473.9505577611824, "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": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 37.36024586658148, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 104 }, { "admitted_plugins": 7, "attempted_matches": 404, "capped_draws": 50, "codegen_cost_usd": { "admitted_cell_count": 7, "cell_count": 8, "cost_basis_counts": { "provider_reported": 33 }, "evidence_basis": "Provider-reported", "failed_cell_count": 9, "max": 0.2156775, "mean": 0.157461515625, "median": 0.15705206249999998, "min": 0.098579625, "recorded_attempt_count": 33, "run_count": 16, "total": 2.51938425 }, "codegen_evaluated_cells": 16, "conditional_success_score": 45.44597930886597, "contributing_entrants": null, "distinct_rated_opponents": 201, "draws": 168, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": 130, "max_score": 68.47656737578293, "measured_at": null, "min_score": 25.16068625041128, "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": 404, "rating_method": "sequential_elo", "raw_elo": 1468.4155253243164, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 7, "repaired_rate": 0.4375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 36.96068238360196, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 106 }, { "admitted_plugins": 7, "attempted_matches": 288, "capped_draws": 53, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 144, "draws": 94, "entry_count": 7, "failed_game_aliases": [], "first_pass_admitted": null, "first_pass_rate": null, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:54:18Z", "losses": 112, "max_score": 53.32304855651662, "measured_at": null, "min_score": 20.745733263714285, "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": "provisional", "rated_matches": 288, "rating_method": "sequential_elo", "raw_elo": 1447.0488191118857, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 35.241132026567165, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 82 }, { "admitted_plugins": 4, "attempted_matches": 214, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 4, "cell_count": 8, "cost_basis_counts": { "provider_reported": 17 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.0711619, "mean": 0.0371769625, "median": 0.029592175, "min": 0.02387735, "recorded_attempt_count": 17, "run_count": 8, "total": 0.2974157 }, "codegen_evaluated_cells": 8, "conditional_success_score": 40.98023139587708, "contributing_entrants": null, "distinct_rated_opponents": 107, "draws": 92, "entry_count": 4, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:23:02Z", "losses": 64, "max_score": 53.536938067285334, "measured_at": null, "min_score": 32.827810893590744, "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": 214, "rating_method": "sequential_elo", "raw_elo": 1496.2164258090877, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 4, "repaired_rate": 0.5, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 34.460129677060756, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugins": 14, "attempted_matches": 576, "capped_draws": 104, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 288, "draws": 216, "entry_count": 14, "failed_game_aliases": [], "first_pass_admitted": null, "first_pass_rate": null, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:48:17Z", "losses": 228, "max_score": 51.48147323629893, "measured_at": null, "min_score": 24.11930639666456, "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": "provisional", "rated_matches": 576, "rating_method": "sequential_elo", "raw_elo": 1447.304417416557, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 34.036578645771186, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 132 }, { "admitted_plugins": 5, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 37 }, "evidence_basis": "Provider-reported", "failed_cell_count": 11, "max": 0.213668025, "mean": 0.180929025625, "median": 0.1746528825, "min": 0.16318875, "recorded_attempt_count": 37, "run_count": 16, "total": 2.89486441 }, "codegen_evaluated_cells": 16, "conditional_success_score": 43.76808690498887, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": 73, "entry_count": 5, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-26T02:15:57Z", "losses": 80, "max_score": 55.633695043376434, "measured_at": null, "min_score": 21.92797491218185, "model_code_failure_rate": 0.6875, "model_code_failures": 11, "model_display_name": "Inkling", "model_slug": "thinkingmachines-inkling", "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": 0, "rating_method": "sequential_elo", "raw_elo": 1440.8641223893603, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Max", "reasoning_bracket": "intensive", "reasoning_bucket": "max", "reasoning_bucket_label": "Max", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "max" }, "repaired_admitted": 5, "repaired_rate": 0.3125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 32.72427770487978, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugins": 5, "attempted_matches": 202, "capped_draws": 68, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 101, "draws": 135, "entry_count": 5, "failed_game_aliases": [], "first_pass_admitted": null, "first_pass_rate": null, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:26:42Z", "losses": 43, "max_score": 51.110878446006915, "measured_at": null, "min_score": 21.605010778009973, "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": "provisional", "rated_matches": 202, "rating_method": "sequential_elo", "raw_elo": 1445.854469940611, "reasoning_level": "Highest", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": null, "requested_effort": "highest", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Highest", "reasoning_bracket": "intensive", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 31.61899034274135, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 7, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 7, "cell_count": 8, "cost_basis_counts": { "provider_reported": 34 }, "evidence_basis": "Provider-reported", "failed_cell_count": 8, "max": 0.0, "mean": 0.0, "median": 0.0, "min": 0.0, "recorded_attempt_count": 34, "run_count": 15, "total": 0.0 }, "codegen_evaluated_cells": 15, "conditional_success_score": 36.361429751934864, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": 84, "entry_count": 7, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "GB2-05", "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 }, "infra_excluded_game_aliases": [ "GB2-05" ], "infra_failures_excluded": 1, "is_recent_addition": false, "last_measured_at": "2026-07-26T04:32:32Z", "losses": 130, "max_score": 42.89789158042775, "measured_at": null, "min_score": 29.824967923441967, "model_code_failure_rate": 0.5333333333333333, "model_code_failures": 8, "model_display_name": "Ling 3.0 Flash", "model_slug": "inclusionai-ling-3-0-flash", "plugin_success_rate": 0.4666666666666667, "provider": "InclusionAI", "provider_key": "inclusionai", "rank": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "provisional", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1407.246967886118, "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": true, "evidence_status": "retained_exact", "request_mode": "toggle", "requested_effort": "enabled", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 7, "repaired_rate": 0.4666666666666667, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 30.053333230294538, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 68 }, { "admitted_plugins": 4, "attempted_matches": 252, "capped_draws": 53, "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": 0.0429946875, "median": 0.0423105, "min": 0.0223935, "recorded_attempt_count": 14, "run_count": 8, "total": 0.34395749999999997 }, "codegen_evaluated_cells": 8, "conditional_success_score": 32.10501667536629, "contributing_entrants": null, "distinct_rated_opponents": 125, "draws": 58, "entry_count": 4, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:31Z", "losses": 113, "max_score": 38.70088877553203, "measured_at": null, "min_score": 25.961097857676517, "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": 249, "rating_method": "sequential_elo", "raw_elo": 1401.2485940757429, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 26.996993433976236, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 3, "wins": 78 }, { "admitted_plugins": 5, "attempted_matches": 212, "capped_draws": 23, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 106, "draws": 58, "entry_count": 5, "failed_game_aliases": [], "first_pass_admitted": null, "first_pass_rate": null, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:18:10Z", "losses": 107, "max_score": 40.02316688669191, "measured_at": null, "min_score": 0.0, "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": "provisional", "rated_matches": 212, "rating_method": "sequential_elo", "raw_elo": 1340.8690817061367, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 23.388684213793677, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugins": 5, "attempted_matches": 324, "capped_draws": 110, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 29 }, "evidence_basis": "Provider-reported", "failed_cell_count": 11, "max": 0.0, "mean": 0.0, "median": 0.0, "min": 0.0, "recorded_attempt_count": 29, "run_count": 16, "total": 0.0 }, "codegen_evaluated_cells": 16, "conditional_success_score": 27.36940382474815, "contributing_entrants": null, "distinct_rated_opponents": 160, "draws": 110, "entry_count": 5, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:36:23Z", "losses": 154, "max_score": 27.58246377184411, "measured_at": null, "min_score": 27.1563438776522, "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": 324, "rating_method": "sequential_elo", "raw_elo": 1377.562628113915, "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": "other", "provider_model": "cohere/north-mini-code", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 20.46340232604428, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4, "attempted_matches": 142, "capped_draws": 4, "codegen_cost_usd": { "admitted_cell_count": 4, "cell_count": 8, "cost_basis_counts": { "provider_reported": 13 }, "evidence_basis": "Provider-reported", "failed_cell_count": 5, "max": 0.33185775, "mean": 0.18266821875, "median": 0.16804049999999998, "min": 0.08751, "recorded_attempt_count": 13, "run_count": 9, "total": 1.7932035000000002 }, "codegen_evaluated_cells": 9, "conditional_success_score": 21.2286991885296, "contributing_entrants": null, "distinct_rated_opponents": 71, "draws": 19, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:30:30Z", "losses": 195, "max_score": 28.364274717844992, "measured_at": null, "min_score": 14.82966031579288, "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": 142, "rating_method": "sequential_elo", "raw_elo": 1304.9356889116953, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 2, "repaired_rate": 0.2222222222222222, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 17.33316030497761, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T10:51:16Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1902.50819139413, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 58 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T11:24:40Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1828.996677787992, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 90.56767341997636, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 54 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:25:45Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1819.728353888386, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 89.02948337376621, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 47 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 19, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 19, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T10:50:16Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1726.5259512130235, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 77.1650058104334, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 29 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 16, "max_score": null, "measured_at": "2026-07-27T10:47:12Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1715.0185204641425, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 75.5601349974072, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 42 }, { "admitted_plugins": 1, "attempted_matches": 72, "capped_draws": 15, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 36, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:20:39Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 72, "rating_method": "sequential_elo", "raw_elo": 1676.59501851212, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 71.25680984831166, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 42 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T11:25:35Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1661.6976408495564, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 68.52383229044648, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 36 }, { "admitted_plugins": 2, "attempted_matches": 100, "capped_draws": 44, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 50, "draws": 44, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T10:36:06Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 100, "rating_method": "sequential_elo", "raw_elo": 1663.2578169032925, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 68.33312358571251, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 24, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 24, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:25:54Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1653.411765004077, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 67.56620389662746, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 23 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T10:48:01Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1644.4759251533983, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 66.16530892077893, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 36 }, { "admitted_plugins": 3, "attempted_matches": 208, "capped_draws": 25, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 104, "draws": 25, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 67, "max_score": null, "measured_at": "2026-07-27T11:25:15Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 208, "rating_method": "sequential_elo", "raw_elo": 1631.9565756398863, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 65.32770242067362, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 16.089767264777418, "unilateral_faults": 0, "wins": 116 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 8, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 8, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T11:21:33Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1631.9779985185817, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 65.00304603642252, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 31 }, { "admitted_plugins": 3, "attempted_matches": 98, "capped_draws": 16, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 49, "draws": 34, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 50, "max_score": null, "measured_at": "2026-07-27T10:51:05Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 98, "rating_method": "sequential_elo", "raw_elo": 1645.7131029732216, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 64.63299103911847, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 39.97783371817835, "unilateral_faults": 0, "wins": 126 }, { "admitted_plugins": 2, "attempted_matches": 80, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 40, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-26T05:19:34Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1638.392961019582, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 64.26871280365481, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 50 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T10:47:05Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1623.2307722548098, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 63.53247225350247, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 34 }, { "admitted_plugins": 2, "attempted_matches": 98, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 49, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 34, "max_score": null, "measured_at": "2026-07-27T10:30:27Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 98, "rating_method": "sequential_elo", "raw_elo": 1619.2961858016197, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 62.55535735493004, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 26.97128781498596, "unilateral_faults": 0, "wins": 57 }, { "admitted_plugins": 0, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T10:26:46Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1612.48039153947, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 61.09711900072354, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 22 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 6, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:53:30Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1594.7574022863707, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 59.955367539088286, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 33 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:23:03Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1589.1789388885927, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 58.990116931190066, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 29 }, { "admitted_plugins": 1, "attempted_matches": 76, "capped_draws": 14, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 38, "draws": 14, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:48:31Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1579.7115495088487, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 58.84535558133786, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 43 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 17, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 17, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T11:16:48Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1582.8274794165334, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 58.72679193774028, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 29 }, { "admitted_plugins": 2, "attempted_matches": 134, "capped_draws": 29, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 67, "draws": 29, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 53, "max_score": null, "measured_at": "2026-07-27T11:55:02Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 134, "rating_method": "sequential_elo", "raw_elo": 1578.9605026224492, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 58.36812405939523, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 52 }, { "admitted_plugins": 2, "attempted_matches": 120, "capped_draws": 33, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 60, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T10:36:10Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 120, "rating_method": "sequential_elo", "raw_elo": 1581.1012071463724, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 58.29507221734059, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 61 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 38, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T11:21:38Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1578.7755636434526, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.76408091303755, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 15 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 14, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 14, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-27T11:08:58Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1577.025901566621, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking field omitted", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking field omitted", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.41317066463946, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 23 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T11:48:31Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1576.9979684590764, "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": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 56.67090350467359, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 18, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 18, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:16:35Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1564.6500398829733, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 56.16041187613398, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 18 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 15, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:20:42Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1563.2313436316006, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 56.082660301584646, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 2, "attempted_matches": 76, "capped_draws": 35, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 38, "draws": 65, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-27T11:16:11Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1575.662991828095, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.99220669211011, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 35.655011583130054, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 12, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 12, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:23:03Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1562.54730392307, "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": "omitted", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 54.79582315352283, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 2, "attempted_matches": 76, "capped_draws": 29, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 38, "draws": 65, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:09:22Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1563.4119554419992, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 54.4025443238804, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 35.655011583130054, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 11, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-27T11:54:18Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1551.1970854508706, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.32304855651662, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 3, "attempted_matches": 128, "capped_draws": 22, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 64, "draws": 51, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 85, "max_score": null, "measured_at": "2026-07-27T11:53:12Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 128, "rating_method": "sequential_elo", "raw_elo": 1546.5261237980658, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Max", "reasoning_bracket": "intensive", "reasoning_bucket": "max", "reasoning_bucket_label": "Max", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "max" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.36937197174774, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 34.13401041481541, "unilateral_faults": 0, "wins": 108 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 4, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:53:30Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1534.387956889026, "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-mini", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.12198654872786, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 35 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T10:45:00Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1547.2346974795885, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.729550125281335, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 41.18336395796551, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:17:18Z", "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": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1521.3936825716696, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.19447975472116, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-26T01:14:31Z", "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": 37, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1527.987432545009, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.94278083109678, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 16 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 5, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 20, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:31:19Z", "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": 38, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1527.58898800444, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.426447239287874, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 38.812854461075986, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 14, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 14, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T11:25:54Z", "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": 39, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1508.9996053111847, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.14708051635627, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 24 }, { "admitted_plugins": 2, "attempted_matches": 60, "capped_draws": 30, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 30, "draws": 65, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:22:16Z", "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": 40, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1521.630336835687, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "balanced", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.37070779104473, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 41.534862397692415, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 2, "attempted_matches": 126, "capped_draws": 31, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 63, "draws": 31, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 55, "max_score": null, "measured_at": "2026-07-27T11:31:26Z", "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": 41, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 126, "rating_method": "sequential_elo", "raw_elo": 1503.158468494203, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.3336953705786, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 18.8015810723003, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 20, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 35, "max_score": null, "measured_at": "2026-07-26T05:08:25Z", "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": 42, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1511.9250538429842, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Minimal", "reasoning_bracket": "baseline", "reasoning_bucket": "minimal", "reasoning_bucket_label": "Minimal", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "minimal" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.95394531902585, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 33.41808305530269, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 15, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T10:25:02Z", "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": 43, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1497.3874694861893, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.91834193923778, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32 }, { "admitted_plugins": 1, "attempted_matches": 74, "capped_draws": 27, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 37, "draws": 27, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:31:26Z", "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": 44, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1494.5716412258355, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.71947792576954, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 23 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 20, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 20, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T11:25:45Z", "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": 45, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1500.156493815032, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.5626764936281, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 18 }, { "admitted_plugins": 3, "attempted_matches": 204, "capped_draws": 51, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 102, "draws": 51, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 82, "max_score": null, "measured_at": "2026-07-27T11:54:00Z", "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": 46, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 204, "rating_method": "sequential_elo", "raw_elo": 1495.360690744961, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.554841215429576, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 16.557344098906125, "unilateral_faults": 0, "wins": 71 }, { "admitted_plugins": 2, "attempted_matches": 120, "capped_draws": 68, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 60, "draws": 68, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:55:02Z", "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": 47, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 120, "rating_method": "sequential_elo", "raw_elo": 1498.2804328508075, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.54578462463877, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 24 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 50, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:24:42Z", "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": 48, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1489.9225771870858, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 46.76850942142567, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 7 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 3, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 20, "draws": 10, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:33:29Z", "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": 49, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1507.9573663660651, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 46.577603476802054, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 41.71727501641449, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 2, "attempted_matches": 132, "capped_draws": 41, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 66, "draws": 41, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 48, "max_score": null, "measured_at": "2026-07-27T11:54:00Z", "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": 50, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 132, "rating_method": "sequential_elo", "raw_elo": 1480.535597443261, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.54198211998018, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.416580872281934, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 23, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 23, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:05:07Z", "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": 51, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1480.1694379737794, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.502967642683174, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 22 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 12, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 12, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T10:47:58Z", "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": 52, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1481.3892527994904, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.46304512513314, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 9, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T11:17:05Z", "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": 53, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1483.905475102522, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.19928208402567, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 13, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 13, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:24:40Z", "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": 54, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1479.5735802409645, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.89189158155693, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 18 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:51:16Z", "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": 55, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1495.193047600924, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.818716626603695, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 42.70587299553475, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 16, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 16, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-27T10:37:13Z", "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": 56, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1477.0492603937407, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.68186759149837, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 25 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:33:08Z", "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": 57, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1495.4492714651392, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.64799882230341, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 44.67073949561819, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 17, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-26T04:33:46Z", "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": 58, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1485.3137654013412, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.50093428611456, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 33.41808305530269, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugins": 2, "attempted_matches": 124, "capped_draws": 35, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 62, "draws": 35, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 53, "max_score": null, "measured_at": "2026-07-27T11:48:36Z", "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": 59, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 124, "rating_method": "sequential_elo", "raw_elo": 1471.1495141356838, "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": true, "evidence_status": "retained_exact", "request_mode": "toggle", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.131890322774105, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 36 }, { "admitted_plugins": 4, "attempted_matches": 176, "capped_draws": 23, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 88, "draws": 23, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 80, "max_score": null, "measured_at": "2026-07-27T11:54:18Z", "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": 60, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1479.3211820076922, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.99088017788524, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.8408904576248, "unilateral_faults": 0, "wins": 73 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:05:07Z", "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": 61, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1483.123014784552, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.91604697226371, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 12, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 12, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T10:47:44Z", "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": 62, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1472.4808055170065, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.84767304178936, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 19 }, { "admitted_plugins": 3, "attempted_matches": 194, "capped_draws": 32, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 97, "draws": 32, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 88, "max_score": null, "measured_at": "2026-07-27T11:25:52Z", "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": 63, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 194, "rating_method": "sequential_elo", "raw_elo": 1467.8106521935588, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.80108841581784, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 18.28106122889297, "unilateral_faults": 0, "wins": 74 }, { "admitted_plugins": 2, "attempted_matches": 84, "capped_draws": 25, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 42, "draws": 25, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T10:26:48Z", "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": 64, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 84, "rating_method": "sequential_elo", "raw_elo": 1478.9713630017695, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.773337420402555, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 22 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 29, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 29, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 16, "max_score": null, "measured_at": "2026-07-27T10:33:16Z", "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": 65, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1458.4305805417964, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.26595649843005, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 13 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T11:25:46Z", "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": 66, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1450.988870016457, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.41203641046077, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 27 }, { "admitted_plugins": 2, "attempted_matches": 122, "capped_draws": 30, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 61, "draws": 30, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 53, "max_score": null, "measured_at": "2026-07-27T10:50:15Z", "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": 67, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 122, "rating_method": "sequential_elo", "raw_elo": 1450.462126069157, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.39685486271934, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 19.7562594006596, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugins": 2, "attempted_matches": 88, "capped_draws": 35, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 44, "draws": 35, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:47:56Z", "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": 68, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 88, "rating_method": "sequential_elo", "raw_elo": 1455.6399619899837, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.92380669690927, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 38, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T11:07:18Z", "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": 69, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1445.0343615965558, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking field omitted", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking field omitted", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.41017310675189, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 10 }, { "admitted_plugins": 2, "attempted_matches": 74, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 37, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 69, "max_score": null, "measured_at": "2026-07-27T11:17:15Z", "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": 70, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1457.4978861248828, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.22743264582813, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 39.81642880532208, "unilateral_faults": 0, "wins": 56 }, { "admitted_plugins": 4, "attempted_matches": 66, "capped_draws": 11, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 5, "distinct_rated_opponents": 33, "draws": 65, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 47, "max_score": null, "measured_at": "2026-07-27T11:53:12Z", "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": 71, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1486.968427070579, "reasoning_level": "Extended thinking (legacy shared budget)", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_exact", "request_mode": "effort", "requested_effort": "legacy_shared_thinking_budget", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Extended thinking (legacy shared budget)", "reasoning_bracket": "intensive", "reasoning_bucket": "legacy_shared_thinking_budget", "reasoning_bucket_label": "Extended thinking (legacy shared budget)", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "legacy_shared_thinking_budget" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.07404605347577, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 49.14720687319004, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugins": 1, "attempted_matches": 76, "capped_draws": 24, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 38, "draws": 24, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:26:17Z", "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": 72, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1431.6560101881555, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.63405689209577, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 23 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 27, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-26T04:31:49Z", "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": 73, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1432.9266307142595, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.79869365428509, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 30, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-26T02:18:45Z", "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": 74, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1427.0613921129166, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Minimal", "reasoning_bracket": "baseline", "reasoning_bucket": "minimal", "reasoning_bucket_label": "Minimal", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "minimal" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.84688237866748, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 19 }, { "admitted_plugins": 4, "attempted_matches": 260, "capped_draws": 76, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 130, "draws": 76, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 117, "max_score": null, "measured_at": "2026-07-27T11:37:35Z", "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": 75, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 260, "rating_method": "sequential_elo", "raw_elo": 1411.2303820418765, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.489269004581146, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.99313799115447, "unilateral_faults": 0, "wins": 67 }, { "admitted_plugins": 3, "attempted_matches": 196, "capped_draws": 65, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 98, "draws": 65, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 86, "max_score": null, "measured_at": "2026-07-27T11:20:42Z", "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": 76, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 196, "rating_method": "sequential_elo", "raw_elo": 1405.0885978520623, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.72273833543881, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.700176346389366, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 18, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 18, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T11:22:15Z", "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": 77, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1406.1009817298916, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.358279790014166, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 16 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 11, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:09:22Z", "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": 78, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1413.0817228894214, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.827672532836864, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 24, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:25:46Z", "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": 79, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1413.8795717766495, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.19470044445362, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 43.40903824311957, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 6, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T11:16:08Z", "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": 80, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 61, "rating_method": "sequential_elo", "raw_elo": 1393.6204375879504, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.02186953365919, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 19.750063500095248, "unilateral_faults": 3, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 4, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 40, "max_score": null, "measured_at": "2026-07-27T10:33:29Z", "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": 81, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1409.681447736922, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.92438548422537, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 2, "attempted_matches": 122, "capped_draws": 33, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 61, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 49, "max_score": null, "measured_at": "2026-07-27T11:26:27Z", "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": 82, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 122, "rating_method": "sequential_elo", "raw_elo": 1381.0155302257313, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.38564662410492, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 19.7562594006596, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 18, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 18, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:07:18Z", "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": 83, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1378.486150271109, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.3088107693705, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 16 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 18, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:51:06Z", "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": 84, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1392.986063334523, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.19459609318916, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.19324853318743, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 16, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 16, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:08:57Z", "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": 85, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 59, "rating_method": "sequential_elo", "raw_elo": 1357.846690093915, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.271001037603703, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 20.79972243679028, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 15, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:21:50Z", "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": 86, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1359.6393456579792, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.205660998009655, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 14 }, { "admitted_plugins": 2, "attempted_matches": 132, "capped_draws": 61, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 66, "draws": 61, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 55, "max_score": null, "measured_at": "2026-07-27T11:24:41Z", "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": 87, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 132, "rating_method": "sequential_elo", "raw_elo": 1342.0779950278898, "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": "other", "provider_model": "cohere/north-mini-code", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.58246377184411, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.355146918744417, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 8, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-26T02:18:41Z", "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": 88, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1351.2546228678034, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.010394711158984, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 9 }, { "admitted_plugins": 2, "attempted_matches": 118, "capped_draws": 38, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 59, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 64, "max_score": null, "measured_at": "2026-07-27T11:47:56Z", "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": 89, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 118, "rating_method": "sequential_elo", "raw_elo": 1337.52818990007, "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-nano", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.6338275876808, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 20.80644772842997, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 2, "attempted_matches": 122, "capped_draws": 57, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 61, "draws": 57, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 50, "max_score": null, "measured_at": "2026-07-27T10:30:48Z", "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": 90, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 122, "rating_method": "sequential_elo", "raw_elo": 1332.7271647404896, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.11987489541008, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 19.7562594006596, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 23, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 23, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-27T08:33:33Z", "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": 91, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1340.1564195017108, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.105376543268523, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 6 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 19, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T10:51:04Z", "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": 92, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1338.1622966328275, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.74431399881591, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 39.80145244019624, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 42, "capped_draws": 31, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 21, "draws": 31, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T10:30:19Z", "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": 93, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1308.1269234889603, "reasoning_level": "Highest", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": null, "requested_effort": "highest", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Highest", "reasoning_bracket": "intensive", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.605010778009973, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 14, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-26T02:12:15Z", "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": 94, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1301.4844814069097, "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": true, "evidence_status": "retained_exact", "request_mode": "toggle", "requested_effort": "enabled", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 20.552351615993096, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 4, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 45, "max_score": null, "measured_at": "2026-07-27T10:50:09Z", "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": 95, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1302.5506201377443, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 19.617975464814673, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 44.67073949561819, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 4, "attempted_matches": 228, "capped_draws": 51, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 114, "draws": 51, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 138, "max_score": null, "measured_at": "2026-07-27T11:25:52Z", "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": 96, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 228, "rating_method": "sequential_elo", "raw_elo": 1280.700601387579, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 19.139574631625756, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 21.96682519692495, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T11:22:50Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1776.7560641910516, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 43 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 20, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T11:22:56Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1735.4526025988669, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 90.13059941166075, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 35 }, { "admitted_plugins": 2, "attempted_matches": 80, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 40, "draws": 19, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-26T05:18:50Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1697.616249764408, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 78.60604273503697, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 47 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 26, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T11:22:53Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1659.3993318565135, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 71.95778371836957, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 29 }, { "admitted_plugins": 2, "attempted_matches": 98, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 49, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-27T09:25:43Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 98, "rating_method": "sequential_elo", "raw_elo": 1630.3875789807648, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 63.94985004999732, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 26.97128781498596, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 28, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T10:43:03Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1624.075614202798, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 63.51723403185436, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 21 }, { "admitted_plugins": 2, "attempted_matches": 100, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 50, "draws": 49, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T09:25:48Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 100, "rating_method": "sequential_elo", "raw_elo": 1614.1052407283012, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 60.19441308419789, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 37, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:22:54Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1595.2075134501106, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.20745689293141, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 20 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 25, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T10:42:56Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1554.6276258057092, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 46.92274071038185, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 22 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 37, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:10:04Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1547.1720098303158, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.346922229587115, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 13 }, { "admitted_plugins": 2, "attempted_matches": 132, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 66, "draws": 81, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T10:43:03Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 132, "rating_method": "sequential_elo", "raw_elo": 1542.432769124338, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.63145274557937, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 18.087190646312703, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 30, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T10:39:40Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1534.4980840240307, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.89639389555927, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 14 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 39, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T07:55:17Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1527.5674418666176, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.24032728154734, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 7 }, { "admitted_plugins": 2, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 33, "draws": 77, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:22:55Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1536.690260686128, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.93697130952252, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 40.69832562925967, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T09:06:59Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1507.016974397993, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking field omitted", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking field omitted", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.54624651592337, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 62, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T10:49:50Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1501.313222137573, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.77155592483919, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 64, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T11:10:15Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1499.1390170008954, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.43031617632999, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 42, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T10:49:51Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1501.132056255132, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.69550841012682, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 50, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 46, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T10:49:50Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1502.5488228935112, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.53817330743257, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 50, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 48, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T10:46:41Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1502.3246516528714, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.484607923588854, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 3, "attempted_matches": 170, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 85, "draws": 162, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T10:49:51Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 170, "rating_method": "sequential_elo", "raw_elo": 1498.942537588182, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.45694771758166, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 22.181059143734817, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T11:18:10Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1499.278211372801, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.25253493848372, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 7 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 49, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T11:23:02Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1497.5007403786417, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.827810893590744, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1 }, { "admitted_plugins": 2, "attempted_matches": 108, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 54, "draws": 106, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T11:23:02Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 108, "rating_method": "sequential_elo", "raw_elo": 1492.4830875314651, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.570829807726735, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 23.97350569750971, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 48, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 0, "max_score": null, "measured_at": "2026-07-27T10:46:41Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1495.4141301372438, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.562942122426243, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 60, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T10:49:49Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1488.5809352786268, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.542487942751787, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1 }, { "admitted_plugins": 2, "attempted_matches": 128, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 64, "draws": 120, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T11:23:13Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 128, "rating_method": "sequential_elo", "raw_elo": 1486.2711131042715, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.17726639024936, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 58, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 0, "max_score": null, "measured_at": "2026-07-27T10:03:08Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1488.7189255222488, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.173955008668692, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T11:26:34Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1489.9472910874329, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.022925443196662, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1 }, { "admitted_plugins": 1, "attempted_matches": 50, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 0, "max_score": null, "measured_at": "2026-07-27T10:35:34Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1491.9181454193697, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.997988769059855, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 2, "attempted_matches": 118, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 59, "draws": 104, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T11:10:00Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 118, "rating_method": "sequential_elo", "raw_elo": 1484.4713582365905, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.26185005867806, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 20.80644772842997, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 2, "attempted_matches": 136, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 68, "draws": 116, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T11:23:13Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 136, "rating_method": "sequential_elo", "raw_elo": 1480.838308070823, "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-nano", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.195055758003996, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 16.61455287691689, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T10:43:03Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1487.2623907567247, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.140455882095676, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 3, "attempted_matches": 175, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 88, "draws": 146, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:17:58Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 175, "rating_method": "sequential_elo", "raw_elo": 1483.9311490852626, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.05739733199343, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 21.200730137000697, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 3, "attempted_matches": 156, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 78, "draws": 144, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:26:42Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 156, "rating_method": "sequential_elo", "raw_elo": 1487.0053737211565, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.047425320937624, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 25.095677040127953, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 34, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T11:18:10Z", "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": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1495.250360698582, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.873056729095698, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 63, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T11:18:19Z", "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": 37, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1480.524029567731, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.80400934470667, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 56, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T10:49:51Z", "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": 38, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1479.9188889322822, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.659411891774138, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 2, "attempted_matches": 116, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 58, "draws": 105, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T11:22:54Z", "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": 39, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 116, "rating_method": "sequential_elo", "raw_elo": 1481.5020057636186, "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-mini", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.44411630713003, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 63, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T11:18:18Z", "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": 40, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1476.5603955656177, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.205662826109684, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 60, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T11:26:34Z", "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": 41, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1477.653649416274, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.11813628556075, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 2 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T11:23:13Z", "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": 42, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1484.5879724595852, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.976047880768927, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 39, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T10:46:41Z", "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": 43, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1489.8564736994583, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.962153891671328, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 3, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 82, "draws": 149, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:26:38Z", "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": 44, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1481.0444737034147, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.875429548217255, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 23.77555789204983, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 73, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-26T04:32:26Z", "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": 45, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1487.3155765144922, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.8476633604157, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 31.75968834662516, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 57, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T09:27:48Z", "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": 46, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1477.2364928140053, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.8317503237067, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 2 }, { "admitted_plugins": 2, "attempted_matches": 128, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 64, "draws": 123, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T11:26:38Z", "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": 47, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 128, "rating_method": "sequential_elo", "raw_elo": 1476.427219156717, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.820870760406777, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 18.289400506511907, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-26T02:19:22Z", "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": 48, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1489.1522376403848, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.79387773495653, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1, "attempted_matches": 28, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 14, "draws": 63, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T10:35:34Z", "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": 49, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 28, "rating_method": "sequential_elo", "raw_elo": 1495.4643675592058, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.702345229467554, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 42.70587299553475, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 53, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T10:38:09Z", "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": 50, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1498.8227626605349, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.574021625817625, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 47.5751600509567, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 64, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T11:26:28Z", "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": 51, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1473.232701299803, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.573734971782702, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 52, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T10:39:38Z", "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": 52, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1479.6156043304468, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.554184291069387, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 79, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-26T01:24:29Z", "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": 53, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1487.3145592583064, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.354767224454108, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 4, "attempted_matches": 212, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 106, "draws": 195, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T11:10:15Z", "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": 54, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 212, "rating_method": "sequential_elo", "raw_elo": 1479.1796174954648, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.309344060133164, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.405823784913025, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 44, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T10:46:40Z", "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": 55, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1477.334204135014, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking field omitted", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking field omitted", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.009047114593564, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:22:53Z", "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": 56, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1493.573287927545, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.927667006728253, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 44.39456088374059, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 55, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T10:49:49Z", "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": 57, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1475.919430546933, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.899111953447644, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 60, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T11:26:28Z", "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": 58, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1472.8398095919308, "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": true, "evidence_status": "retained_exact", "request_mode": "toggle", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.7811694206549, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3, "attempted_matches": 106, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 53, "draws": 169, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T11:18:05Z", "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": 59, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 106, "rating_method": "sequential_elo", "raw_elo": 1487.5571190487, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Max", "reasoning_bracket": "intensive", "reasoning_bucket": "max", "reasoning_bucket_label": "Max", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "max" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.637499866574228, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 38.39228737690977, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 1, "attempted_matches": 26, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 13, "draws": 52, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T09:03:06Z", "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": 60, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 26, "rating_method": "sequential_elo", "raw_elo": 1496.234358452679, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.632718734896457, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 49.26384793916254, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T11:26:42Z", "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": 61, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1483.571469812471, "reasoning_level": "Highest", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": null, "requested_effort": "highest", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Highest", "reasoning_bracket": "intensive", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.082403158201195, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 76, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-26T01:22:00Z", "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": 62, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1480.0137295267718, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Minimal", "reasoning_bracket": "baseline", "reasoning_bucket": "minimal", "reasoning_bucket_label": "Minimal", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "minimal" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.61024484133727, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 39, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T10:39:37Z", "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": 63, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1477.1586139699823, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.60687800872694, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 3, "attempted_matches": 114, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 57, "draws": 103, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T11:37:26Z", "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": 64, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 114, "rating_method": "sequential_elo", "raw_elo": 1481.097572399547, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.49126905850573, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 77, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-26T02:16:39Z", "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": 65, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1479.3227937021456, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Minimal", "reasoning_bracket": "baseline", "reasoning_bucket": "minimal", "reasoning_bucket_label": "Minimal", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "minimal" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.445146755820858, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 3, "attempted_matches": 84, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 42, "draws": 157, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T10:39:37Z", "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": 66, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 84, "rating_method": "sequential_elo", "raw_elo": 1490.1593860965586, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.396318186763295, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 48.13805601369197, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 57, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T10:49:42Z", "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": 67, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1466.7923583848676, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.336139967911993, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 53, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T10:49:51Z", "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": 68, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1468.5821896697769, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.14588918135212, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 74, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 37, "draws": 108, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T10:46:40Z", "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": 69, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1491.4134151097094, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.098699501503095, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 51.26251078619039, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 35, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T09:04:37Z", "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": 70, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1479.446255038946, "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": "omitted", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.09668923633087, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 2, "attempted_matches": 74, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 37, "draws": 113, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:22:56Z", "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": 71, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1485.6612365441383, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.918855105037668, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 45.01309903675748, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 59, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T09:17:42Z", "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": 72, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1462.112751652437, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.753419845975525, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 46, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T11:48:23Z", "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": 73, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1466.422044691208, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.16068625041128, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 16, "draws": 30, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T10:49:48Z", "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": 74, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1479.8188659817515, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.852438966409498, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T11:26:19Z", "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": 75, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1470.8448216282686, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.41934796442663, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 2, "attempted_matches": 74, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 37, "draws": 68, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T11:23:02Z", "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": 76, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1472.025070521855, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.11930639666456, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 37.38178527761111, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:39:38Z", "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": 77, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1477.4089183486803, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.01242101325399, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 44.67073949561819, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-25T18:00:56Z", "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": 78, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1466.728730509414, "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": true, "evidence_status": "retained_exact", "request_mode": "toggle", "requested_effort": "enabled", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 23.435814126241773, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 2 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 37, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-26T02:14:07Z", "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": 79, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1465.8763415935357, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Max", "reasoning_bracket": "intensive", "reasoning_bucket": "max", "reasoning_bucket_label": "Max", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "max" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 23.232137065202014, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 1, "attempted_matches": 26, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 13, "draws": 56, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T07:52:19Z", "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": 80, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 26, "rating_method": "sequential_elo", "raw_elo": 1473.372937630626, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.896721550174966, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 45.462269258808135, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 21, "draws": 31, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:48:23Z", "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": 81, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1461.1826663180202, "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": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.789449128010855, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 74, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 37, "draws": 108, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T10:46:40Z", "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": 82, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1471.8149295217936, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.448445079116, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 51.09105910444126, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 64, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:37:26Z", "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": 83, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1461.2682908580343, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.27542844920532, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 38.812854461075986, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 4, "attempted_matches": 70, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 5, "distinct_rated_opponents": 35, "draws": 139, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-27T11:23:02Z", "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": 84, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1469.462162527477, "reasoning_level": "Extended thinking (legacy shared budget)", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_exact", "request_mode": "effort", "requested_effort": "legacy_shared_thinking_budget", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Extended thinking (legacy shared budget)", "reasoning_bracket": "intensive", "reasoning_bucket": "legacy_shared_thinking_budget", "reasoning_bucket_label": "Extended thinking (legacy shared budget)", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "legacy_shared_thinking_budget" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.218380859420797, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 49.35362439738494, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 2, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 31, "draws": 94, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T10:43:03Z", "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": 85, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1488.0188021214274, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "balanced", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 20.580987520067197, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 55.91958998388486, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 53, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:18:01Z", "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": 86, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1458.3997310867876, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 19.179163036226186, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.19324853318743, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 2, "attempted_matches": 80, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 40, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-26T05:19:07Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1818.3922130275887, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 99.01057790596052, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 73 }, { "admitted_plugins": 2, "attempted_matches": 80, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 40, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-26T05:18:21Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1776.563151472152, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 91.93118700577348, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 65 }, { "admitted_plugins": 1, "attempted_matches": 42, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 21, "draws": 20, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T08:03:33Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1640.156750580333, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 69.09378758500024, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 18 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 3, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T08:02:31Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1596.3466678596478, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 61.911144518391616, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 12, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:52:52Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1594.5085265402074, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 61.60004691193783, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 1, "attempted_matches": 50, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 14, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T11:52:57Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1586.8467498305283, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 60.91553236200583, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 2, "attempted_matches": 60, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 30, "draws": 28, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T11:04:58Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1583.1305040657564, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 58.36864528288711, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 40.429265925240735, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugins": 2, "attempted_matches": 104, "capped_draws": 5, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 52, "draws": 37, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T11:10:15Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 104, "rating_method": "sequential_elo", "raw_elo": 1559.337130627261, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 56.435256830019185, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.966995223862348, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 29, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T11:02:46Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1557.0056967199416, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.46990711066279, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 11 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 10, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-26T04:32:18Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1555.427920742531, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Minimal", "reasoning_bracket": "baseline", "reasoning_bucket": "minimal", "reasoning_bucket_label": "Minimal", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "minimal" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.20287523182865, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 21 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 8, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 35, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T10:58:07Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1543.043331713756, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking field omitted", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking field omitted", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.68257145959784, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 42, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 21, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T10:19:29Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1548.5258455371809, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.585646325873974, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 18 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 20, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:18:16Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1537.2180654375327, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.69666989897096, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 32, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-26T04:27:36Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1536.9110831145465, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Minimal", "reasoning_bracket": "baseline", "reasoning_bucket": "minimal", "reasoning_bucket_label": "Minimal", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "minimal" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.49549503671918, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 33.41808305530269, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 15, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:48:17Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1546.9358887216838, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.48147323629893, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 42, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 21, "draws": 19, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:58:08Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1532.8195170122888, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.9274169728892, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 15 }, { "admitted_plugins": 3, "attempted_matches": 156, "capped_draws": 16, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 78, "draws": 70, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T11:52:52Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 156, "rating_method": "sequential_elo", "raw_elo": 1525.3124264162536, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.60736443084445, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 25.479237126358175, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 28, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T10:58:00Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1525.5217643839485, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.14138536541297, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 9 }, { "admitted_plugins": 2, "attempted_matches": 96, "capped_draws": 12, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 48, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T11:37:44Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 96, "rating_method": "sequential_elo", "raw_elo": 1523.1433202477533, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.94247004323288, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugins": 2, "attempted_matches": 82, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 41, "draws": 12, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T11:48:28Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 82, "rating_method": "sequential_elo", "raw_elo": 1527.3550606101735, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.87817883970666, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 33.41808305530269, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 2, "attempted_matches": 102, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 51, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:31:38Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 102, "rating_method": "sequential_elo", "raw_elo": 1520.5623366481875, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.78746785854181, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 25.597143087872503, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugins": 3, "attempted_matches": 146, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 73, "draws": 93, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T11:03:11Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 146, "rating_method": "sequential_elo", "raw_elo": 1520.0022000607769, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.45153806809078, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 27.37805230829621, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 20, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T10:18:25Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 39, "rating_method": "sequential_elo", "raw_elo": 1525.5179367164974, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.31150841617975, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 35.30694150420948, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 6, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 21, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:05:36Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1522.423633843672, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.91915370704513, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 9 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 17, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-26T02:12:12Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1520.7487899584455, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.6356934973392, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 35 }, { "admitted_plugins": 3, "attempted_matches": 136, "capped_draws": 29, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 68, "draws": 77, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:44:52Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 136, "rating_method": "sequential_elo", "raw_elo": 1514.5537109582262, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.172020366997366, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.01758738954685, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 15, "draws": 10, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:18:20Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1527.2252132901654, "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": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.1455251873211, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 10, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 23, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T11:38:14Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1507.1274179692712, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.77459545300492, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 13 }, { "admitted_plugins": 2, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 19, "draws": 20, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T11:44:47Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1530.631146017652, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "balanced", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.41563774645095, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 55.70080376775669, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 24, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T11:44:47Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1504.641480334261, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.64189418693135, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 24, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 16, "max_score": null, "measured_at": "2026-07-27T11:02:50Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1492.4298015489974, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.28708633683153, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 14 }, { "admitted_plugins": 1, "attempted_matches": 18, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 9, "draws": 35, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T10:19:29Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 18, "rating_method": "sequential_elo", "raw_elo": 1520.7807241906676, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.933996869115965, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 61.71645590010924, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 2, "attempted_matches": 96, "capped_draws": 8, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 48, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T10:19:17Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 96, "rating_method": "sequential_elo", "raw_elo": 1491.4955399082585, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.58016839641555, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 27.72324997517388, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 13, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-26T01:22:06Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1487.6875843006812, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.04022494558611, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 14 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 15, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 32, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T11:44:52Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1487.0489962766576, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.932146636436144, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 19, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T09:13:01Z", "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": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1482.3818845275205, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.8401440385904, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 14 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 13, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:30:40Z", "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": 37, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1485.0924616716402, "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": "omitted", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.333305859069256, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 18, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 9, "draws": 27, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T08:02:37Z", "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": 38, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 18, "rating_method": "sequential_elo", "raw_elo": 1498.0276047760062, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.31105096947438, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 52.64737393979195, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 2, "attempted_matches": 102, "capped_draws": 8, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 51, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:54:30Z", "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": 39, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 102, "rating_method": "sequential_elo", "raw_elo": 1475.2414972738902, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.117108402114056, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 25.597143087872503, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugins": 2, "attempted_matches": 106, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 53, "draws": 44, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 34, "max_score": null, "measured_at": "2026-07-27T11:31:38Z", "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": 40, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 106, "rating_method": "sequential_elo", "raw_elo": 1472.639729959869, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.7947922039493, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.72546785769763, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 3, "attempted_matches": 124, "capped_draws": 6, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 62, "draws": 46, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 44, "max_score": null, "measured_at": "2026-07-27T11:48:17Z", "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": 41, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 124, "rating_method": "sequential_elo", "raw_elo": 1478.826703359781, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.66259225389678, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 33.435575077886185, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 6, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 15, "draws": 19, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T11:30:40Z", "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": 42, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1483.8175424040835, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.79896136680666, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 19, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T10:03:28Z", "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": 43, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1471.7215759387857, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.338045883793995, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 8 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 35, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 34, "max_score": null, "measured_at": "2026-07-26T03:31:46Z", "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": 44, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1467.727157847934, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.298818357212, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 29.63358145932378, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 1, "attempted_matches": 26, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 13, "draws": 30, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T11:36:40Z", "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": 45, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 26, "rating_method": "sequential_elo", "raw_elo": 1486.0822555481582, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.05712610425944, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 54.36252243246881, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 15, "draws": 21, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T00:11:53Z", "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": 46, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1478.271732610354, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.860356628188114, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 22, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 11, "draws": 17, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-27T10:19:02Z", "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": 47, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 21, "rating_method": "sequential_elo", "raw_elo": 1488.8943604301728, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.83067183067213, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 59.5501790889026, "unilateral_faults": 1, "wins": 11 }, { "admitted_plugins": 1, "attempted_matches": 20, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 10, "draws": 22, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:48:47Z", "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": 48, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 20, "rating_method": "sequential_elo", "raw_elo": 1484.771748750963, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.653453444576584, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 55.70579806569183, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 5, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 23, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:52:56Z", "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": 49, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1461.662536911419, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.63559627801959, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 7 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 28, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T08:10:00Z", "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": 50, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1457.46717560364, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.62343543749571, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 10 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 14, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T10:18:52Z", "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": 51, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1458.1644256131383, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.52438727472494, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 3, "attempted_matches": 152, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 76, "draws": 61, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 53, "max_score": null, "measured_at": "2026-07-27T11:37:44Z", "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": 52, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 152, "rating_method": "sequential_elo", "raw_elo": 1451.0828773497008, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.956034447719695, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 26.131352980601804, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 23, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T11:48:11Z", "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": 53, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1436.7909872054654, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.848972779507136, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1, "attempted_matches": 50, "capped_draws": 3, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 39, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:02:50Z", "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": 54, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1441.1397761187798, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.25524629697736, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 23, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-26T02:18:23Z", "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": 55, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1445.4058897559369, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.88422783559002, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 6 }, { "admitted_plugins": 2, "attempted_matches": 100, "capped_draws": 6, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 50, "draws": 46, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:48:11Z", "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": 56, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 100, "rating_method": "sequential_elo", "raw_elo": 1437.3954080780577, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.61605485008677, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 26.304426701457977, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 3, "attempted_matches": 88, "capped_draws": 10, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 44, "draws": 46, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T11:54:30Z", "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": 57, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 88, "rating_method": "sequential_elo", "raw_elo": 1452.8816556321274, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.413074688495364, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 47.161388718300266, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 3, "attempted_matches": 42, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 21, "draws": 24, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 41, "max_score": null, "measured_at": "2026-07-27T11:52:57Z", "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": 58, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1462.8635487788483, "reasoning_level": "Extended thinking (legacy shared budget)", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_exact", "request_mode": "effort", "requested_effort": "legacy_shared_thinking_budget", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Extended thinking (legacy shared budget)", "reasoning_bracket": "intensive", "reasoning_bucket": "legacy_shared_thinking_budget", "reasoning_bucket_label": "Extended thinking (legacy shared budget)", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "legacy_shared_thinking_budget" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.6344898738303, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 65.38915666892314, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 1, "attempted_matches": 42, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 21, "draws": 26, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:44:41Z", "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": 59, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1435.8623185574695, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.51782318989246, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 5 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 28, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:44:30Z", "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": 60, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1431.961147134627, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.30664851641847, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 7 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 3, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 13, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T10:19:15Z", "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": 61, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1425.7024844756863, "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-nano", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.451022699687655, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 27, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T11:05:07Z", "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": 62, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1424.386156653482, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.02461357020887, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 6 }, { "admitted_plugins": 1, "attempted_matches": 22, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 11, "draws": 23, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:44:41Z", "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": 63, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 22, "rating_method": "sequential_elo", "raw_elo": 1435.792509312745, "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": "other", "provider_model": "cohere/north-mini-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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.48623719869417, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 54.80243805853167, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 24, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T09:28:28Z", "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": 64, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1411.064865920198, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.973667967146064, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 17, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T10:19:17Z", "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": 65, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1409.5840570079213, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.519421112195783, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 9 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 24, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:52:56Z", "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": 66, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1403.617820599916, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.256036000566052, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 11 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 15, "draws": 18, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:31:27Z", "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": 67, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1419.261890549445, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.873191643532166, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 96, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 48, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 41, "max_score": null, "measured_at": "2026-07-27T08:56:36Z", "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": 68, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 96, "rating_method": "sequential_elo", "raw_elo": 1394.10982893775, "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": true, "evidence_status": "retained_exact", "request_mode": "toggle", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.098050691260877, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 27.72324997517388, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 19, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:03:09Z", "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": 69, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1457.5588113209724, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.89145366159343, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 73.02632550669372, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 50, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 14, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 27, "max_score": null, "measured_at": "2026-07-27T11:05:36Z", "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": 70, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1351.7838803092702, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.132140682151817, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 2, "attempted_matches": 68, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 34, "draws": 37, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 60, "max_score": null, "measured_at": "2026-07-27T11:05:06Z", "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": 71, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1352.8740700973729, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 19.6056169247618, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 38.90120295341135, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T11:22:49Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1821.193278726695, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 46 }, { "admitted_plugins": 2, "attempted_matches": 80, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 40, "draws": 20, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-26T05:19:00Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1697.2745450187056, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 73.42468015070315, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 49 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-26T05:17:50Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1669.0314085778646, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 68.61993149054801, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 26, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T11:22:41Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1653.7320041970793, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 66.45071005956129, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 27, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T10:35:48Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1617.3769690127422, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 60.360340816834494, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 30, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:09:56Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1579.7087489959974, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.71452593995635, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 34, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T08:41:56Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1569.103382231883, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.13435586825387, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 15 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 24, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T10:53:10Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1566.7841216373108, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.32044382130511, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 17 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 27, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T10:30:15Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1560.7829388596697, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.305404528632984, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 19 }, { "admitted_plugins": 2, "attempted_matches": 104, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 52, "draws": 37, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:51:49Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 104, "rating_method": "sequential_elo", "raw_elo": 1562.4138188466493, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.05298165377025, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.966995223862348, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugins": 3, "attempted_matches": 94, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 47, "draws": 77, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 41, "max_score": null, "measured_at": "2026-07-27T11:22:46Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 94, "rating_method": "sequential_elo", "raw_elo": 1567.101366482504, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Max", "reasoning_bracket": "intensive", "reasoning_bucket": "max", "reasoning_bucket_label": "Max", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "max" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 46.192829786225445, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 42.49878111612754, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 39, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T10:53:02Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1548.729486332967, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 46.07577553411435, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 14 }, { "admitted_plugins": 3, "attempted_matches": 174, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 87, "draws": 116, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T10:58:56Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 174, "rating_method": "sequential_elo", "raw_elo": 1549.3135275728098, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 46.0004231200324, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 21.47132379806021, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 2, "attempted_matches": 128, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 64, "draws": 77, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T10:53:09Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 128, "rating_method": "sequential_elo", "raw_elo": 1545.9269827773976, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.804624380131344, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 30 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 43, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:29:48Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1533.6717755962163, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.23945167121127, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 11 }, { "admitted_plugins": 2, "attempted_matches": 100, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 50, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T10:48:26Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 100, "rating_method": "sequential_elo", "raw_elo": 1538.2157242898909, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.019463779962486, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 26.304426701457977, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 32, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:53:12Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1535.795958549268, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.75642364948741, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 74, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 37, "draws": 69, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T10:45:27Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1520.6818659965604, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.48990096796995, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:02:36Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1529.4343084381378, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking field omitted", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking field omitted", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.48915163819359, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 50, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 42, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T08:31:20Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1526.1505400202454, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.6224615828462, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 57, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-26T05:18:59Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1526.9657349005845, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Minimal", "reasoning_bracket": "baseline", "reasoning_bucket": "minimal", "reasoning_bucket_label": "Minimal", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "minimal" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.71926929378232, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 32.95048007367414, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:22:46Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1515.0969212350349, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.376003042374144, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 12 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 59, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T10:43:48Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1512.834046928935, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.08847356683884, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 2 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 40, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T10:53:01Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1513.1147492207922, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.809666551358085, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 48, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T10:58:02Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1517.8546980180151, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.74445802482134, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 49, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T08:29:49Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1510.4667796354577, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.61690227136209, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 8 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 17, "draws": 29, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T07:29:58Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1527.3928154870323, "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": "omitted", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.55892538039321, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 3, "attempted_matches": 200, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 100, "draws": 145, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 27, "max_score": null, "measured_at": "2026-07-27T10:58:56Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 200, "rating_method": "sequential_elo", "raw_elo": 1504.06188219994, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.60021583373031, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.617608894322856, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 2, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 30, "draws": 66, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T11:05:41Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1520.5747166006124, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.23936078612753, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 40.52299760510738, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 1, "attempted_matches": 24, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 12, "draws": 13, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T09:05:32Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 24, "rating_method": "sequential_elo", "raw_elo": 1529.6913005047602, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.549112144936515, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 56.25, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 46, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T10:52:42Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1496.2226687102534, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.93505786860947, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 6 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 49, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:52:49Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1494.2473590945217, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.83231653302763, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 11 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 22, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T10:53:10Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1518.91404152128, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.7846857638282, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 47.5751600509567, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 34, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T08:21:31Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1508.141304108455, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.74840773334668, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 42, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:05:28Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1496.0402265733064, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.57981567734945, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 7 }, { "admitted_plugins": 2, "attempted_matches": 102, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 51, "draws": 83, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T10:52:53Z", "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": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 102, "rating_method": "sequential_elo", "raw_elo": 1499.5984918963782, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.42714387532118, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 25.674278837447822, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 4, "attempted_matches": 148, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 74, "draws": 103, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T10:48:24Z", "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": 37, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 148, "rating_method": "sequential_elo", "raw_elo": 1507.548288827742, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.14502822780986, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 37.38178527761111, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 2, "attempted_matches": 130, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 63, "draws": 98, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T10:48:25Z", "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": 38, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 124, "rating_method": "sequential_elo", "raw_elo": 1489.3127842819954, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.401973606580675, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 19.250031750047626, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 2, "attempted_matches": 125, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 62, "draws": 83, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T10:45:29Z", "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": 39, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 124, "rating_method": "sequential_elo", "raw_elo": 1488.8990253241063, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.32049946583581, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 23 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T10:43:48Z", "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": 40, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1489.7668442731074, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.15864897798004, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 42, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 21, "draws": 36, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T07:29:08Z", "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": 41, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1497.0294371743323, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.82771565073253, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 2, "attempted_matches": 118, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 59, "draws": 87, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T10:58:30Z", "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": 42, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 118, "rating_method": "sequential_elo", "raw_elo": 1487.2679557249785, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.746597116010264, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 20.80644772842997, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 1, "attempted_matches": 50, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T10:52:51Z", "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": 43, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1491.333286691229, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.686693364975824, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 41, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T11:05:41Z", "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": 44, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1490.2406649219877, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.243606728345505, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 27, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T10:48:31Z", "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": 45, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1495.9623564264125, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.00720768323213, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 28, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T08:45:33Z", "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": 46, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1495.7904116780787, "reasoning_level": "Highest", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": null, "requested_effort": "highest", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Highest", "reasoning_bracket": "intensive", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.97295544313002, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 32, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T10:03:17Z", "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": 47, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1487.5701896988592, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.47196362002854, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 7 }, { "admitted_plugins": 2, "attempted_matches": 72, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 36, "draws": 35, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T10:43:48Z", "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": 48, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 72, "rating_method": "sequential_elo", "raw_elo": 1493.572395842094, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.17642355544414, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 38.53975118769762, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugins": 1, "attempted_matches": 24, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 12, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T10:50:03Z", "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": 49, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 24, "rating_method": "sequential_elo", "raw_elo": 1505.9919152699777, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.12887382515068, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 54.36252243246881, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 55, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T10:43:48Z", "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": 50, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1477.6032838196008, "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": true, "evidence_status": "retained_exact", "request_mode": "toggle", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.907085942540736, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1 }, { "admitted_plugins": 2, "attempted_matches": 130, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 65, "draws": 82, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:22:49Z", "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": 51, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 130, "rating_method": "sequential_elo", "raw_elo": 1476.49235088285, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.882383562863147, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 19.03477987847802, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 3, "attempted_matches": 180, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 90, "draws": 129, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T10:52:42Z", "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": 52, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 180, "rating_method": "sequential_elo", "raw_elo": 1477.4032418008044, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.776589675258645, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 20.8372443910451, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T08:39:01Z", "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": 53, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1480.2355614499472, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.688519104226355, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 36, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T11:10:04Z", "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": 54, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1477.865432695363, "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-mini", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.60740336660926, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 8 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 34, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:02:41Z", "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": 55, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1481.9095702707032, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking field omitted", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking field omitted", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.08886348521295, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 40, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T11:07:51Z", "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": 56, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1470.1339268004403, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.738052083219, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 36, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T10:48:25Z", "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": 57, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1480.001540532111, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.70877457082836, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 2, "attempted_matches": 114, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 57, "draws": 87, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-27T10:51:30Z", "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": 58, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 114, "rating_method": "sequential_elo", "raw_elo": 1472.8755524653086, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.70360759272194, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 10 }, { "admitted_plugins": 2, "attempted_matches": 112, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 56, "draws": 80, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T10:51:47Z", "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": 59, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 112, "rating_method": "sequential_elo", "raw_elo": 1472.803460952347, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.55482235515263, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 22.75404151813585, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 66, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-26T02:18:41Z", "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": 60, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1479.7916569609888, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Minimal", "reasoning_bracket": "baseline", "reasoning_bucket": "minimal", "reasoning_bucket_label": "Minimal", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "minimal" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.101018497465517, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 5 }, { "admitted_plugins": 1, "attempted_matches": 50, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 40, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T10:53:08Z", "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": 61, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1471.7037725606615, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.776397542600765, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 20, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 10, "draws": 43, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T08:27:58Z", "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": 62, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 20, "rating_method": "sequential_elo", "raw_elo": 1496.3916661363678, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.759754221251917, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 57.22830710326107, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:50:01Z", "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": 63, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1485.8821345908264, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.15567824497275, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 47.88193642139327, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 28, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 14, "draws": 43, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:17:55Z", "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": 64, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 28, "rating_method": "sequential_elo", "raw_elo": 1487.016124867033, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.918714793887677, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 50.78635697673178, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T10:45:32Z", "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": 65, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1471.716990074414, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.177411381216853, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 22, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 11, "draws": 39, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T10:03:23Z", "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": 66, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 22, "rating_method": "sequential_elo", "raw_elo": 1487.659821181334, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.1378078235891, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 56.49112594673751, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 36, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T11:10:06Z", "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": 67, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1478.6670650224664, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.9194705568705, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.62023516889464, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 44, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T10:10:02Z", "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": 68, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1460.2028298284708, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.89874606250913, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 40, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T10:49:59Z", "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": 69, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1454.5510147312568, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.47820671040979, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 9 }, { "admitted_plugins": 2, "attempted_matches": 122, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 61, "draws": 41, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 43, "max_score": null, "measured_at": "2026-07-27T11:18:04Z", "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": 70, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 122, "rating_method": "sequential_elo", "raw_elo": 1454.7985958238055, "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-nano", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.422092307108727, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 19.9056700157024, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugins": 3, "attempted_matches": 166, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 83, "draws": 143, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T11:05:28Z", "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": 71, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 166, "rating_method": "sequential_elo", "raw_elo": 1454.7935010604235, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.84312128528944, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 23.53231309379926, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 18, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 9, "draws": 35, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T10:10:04Z", "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": 72, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 18, "rating_method": "sequential_elo", "raw_elo": 1483.3259674335122, "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": "other", "provider_model": "cohere/north-mini-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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.71086962365695, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 60.027768011903404, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 2, "attempted_matches": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 38, "draws": 78, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:53:10Z", "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": 73, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1473.5659425899894, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "balanced", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.24443459360968, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 50.75459128937461, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 1, "attempted_matches": 18, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 9, "draws": 35, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T10:43:42Z", "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": 74, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 18, "rating_method": "sequential_elo", "raw_elo": 1481.8316556844986, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.144079418299455, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 61.71645590010924, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 22, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 11, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:49:59Z", "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": 75, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 22, "rating_method": "sequential_elo", "raw_elo": 1476.1836514200374, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.12081427726525, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 54.80243805853167, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 3, "attempted_matches": 86, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 43, "draws": 134, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T10:53:41Z", "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": 76, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 86, "rating_method": "sequential_elo", "raw_elo": 1469.7704001821894, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.89649759084934, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 48.19344896390418, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 2, "attempted_matches": 70, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 35, "draws": 88, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T11:04:59Z", "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": 77, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1503.7176031214149, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.895985669966077, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 54.39938126480841, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 28, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 14, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:58:30Z", "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": 78, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 28, "rating_method": "sequential_elo", "raw_elo": 1468.27005544933, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.45352145685857, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 54, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-26T02:19:07Z", "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": 79, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1455.7847295731035, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.31872041058993, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 6 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 17, "draws": 23, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-26T22:08:31Z", "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": 80, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1458.5374385455698, "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": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.842595418716364, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:10:06Z", "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": 81, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1460.9657967166772, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.70397009886288, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 44.67073949561819, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 36, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-26T04:32:32Z", "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": 82, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1450.768790271424, "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": true, "evidence_status": "retained_exact", "request_mode": "toggle", "requested_effort": "enabled", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.61236711374963, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1 }, { "admitted_plugins": 4, "attempted_matches": 92, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 5, "distinct_rated_opponents": 46, "draws": 122, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 43, "max_score": null, "measured_at": "2026-07-27T11:17:55Z", "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": 83, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 92, "rating_method": "sequential_elo", "raw_elo": 1456.572653327024, "reasoning_level": "Extended thinking (legacy shared budget)", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_exact", "request_mode": "effort", "requested_effort": "legacy_shared_thinking_budget", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Extended thinking (legacy shared budget)", "reasoning_bracket": "intensive", "reasoning_bucket": "legacy_shared_thinking_budget", "reasoning_bucket_label": "Extended thinking (legacy shared budget)", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "legacy_shared_thinking_budget" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 23.58160432703607, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.22209416113826, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 22, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T10:34:01Z", "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": 84, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1440.733349521438, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 23.38150584800255, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 3, "attempted_matches": 78, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 39, "draws": 106, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 52, "max_score": null, "measured_at": "2026-07-27T11:17:57Z", "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": 85, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 78, "rating_method": "sequential_elo", "raw_elo": 1453.637313690273, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.814064655201765, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 47.36918912473109, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 28, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-26T04:07:10Z", "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": 86, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1431.6560449045471, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 20.80501417240327, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-26T03:03:30Z", "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": 87, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1429.2136617086594, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 19.697931844478177, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 36.39318729849085, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 16, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:17:57Z", "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": 88, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1434.7932372194414, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 18.677722595601647, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 49.76941398892446, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 18, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 9, "draws": 36, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T00:21:27Z", "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": 89, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 18, "rating_method": "sequential_elo", "raw_elo": 1439.8902675454406, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 18.058264435137527, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 60.027768011903404, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 22, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 11, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T10:52:47Z", "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": 90, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 22, "rating_method": "sequential_elo", "raw_elo": 1422.0102326087713, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 14.420068188974202, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T11:30:34Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1931.051509970191, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 96.73066798261004, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 60 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T11:30:33Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1895.2246300132751, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 92.451262399467, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 56 }, { "admitted_plugins": 2, "attempted_matches": 80, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 40, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-26T05:19:29Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1855.4153070757852, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 86.16060543308876, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 68 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:30:30Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1819.332270454036, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 83.56050300184323, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 53 }, { "admitted_plugins": 2, "attempted_matches": 114, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 57, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T11:10:13Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 114, "rating_method": "sequential_elo", "raw_elo": 1814.2964967335272, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 82.43652527134509, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 85 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-26T05:11:53Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1805.431754344661, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 80.36582674270291, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 40 }, { "admitted_plugins": 2, "attempted_matches": 112, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 56, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:10:13Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 112, "rating_method": "sequential_elo", "raw_elo": 1790.4131145129454, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 79.52963881852078, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 84 }, { "admitted_plugins": 1, "attempted_matches": 72, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 36, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T11:37:20Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 72, "rating_method": "sequential_elo", "raw_elo": 1758.883007674556, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 76.49983872640665, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 80, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 40, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:24:38Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1744.8030888257304, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 75.10136719944344, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 38, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:30:26Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1721.279849578368, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 72.15544813911, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 55 }, { "admitted_plugins": 2, "attempted_matches": 146, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 73, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 54, "max_score": null, "measured_at": "2026-07-27T11:10:13Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 146, "rating_method": "sequential_elo", "raw_elo": 1705.221400737045, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 70.1276647758533, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 14.377800258513927, "unilateral_faults": 0, "wins": 92 }, { "admitted_plugins": 3, "attempted_matches": 214, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 107, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 75, "max_score": null, "measured_at": "2026-07-27T11:10:13Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 214, "rating_method": "sequential_elo", "raw_elo": 1699.4681950681795, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 69.34645655053502, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 15.361567975806963, "unilateral_faults": 0, "wins": 139 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:10:13Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1652.109166288075, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 63.117863543585464, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 37 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T11:03:48Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1639.493660691125, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 61.71380324937027, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 40 }, { "admitted_plugins": 2, "attempted_matches": 134, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 67, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 58, "max_score": null, "measured_at": "2026-07-27T11:26:08Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 133, "rating_method": "sequential_elo", "raw_elo": 1619.6763359283814, "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-nano", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 59.64569065882853, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.139398880661957, "unilateral_faults": 1, "wins": 75 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:26:07Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1616.3524860198763, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 59.31522058212656, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 43 }, { "admitted_plugins": 2, "attempted_matches": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 38, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 40, "max_score": null, "measured_at": "2026-07-27T11:16:49Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1628.4382549178165, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 59.03608650610162, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 34.471251018360036, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:09:34Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1587.9373567546218, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.746785917192774, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 39 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T11:30:33Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1602.9531724861602, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.71385221064524, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 37.38178527761111, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T11:07:21Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1583.9989523111312, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 54.98231754257976, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 35 }, { "admitted_plugins": 2, "attempted_matches": 94, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 47, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 44, "max_score": null, "measured_at": "2026-07-27T11:08:03Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 94, "rating_method": "sequential_elo", "raw_elo": 1586.7624035224435, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 54.63527551118202, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 28.430533588759353, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:20:59Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1578.3209032811378, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 54.40691412278813, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 35 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T10:38:17Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1575.875340508706, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 54.39513803855472, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 35 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:03:41Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1591.4510347559626, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.83120272886001, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 42.70587299553475, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T10:36:15Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1572.8040677708518, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.536938067285334, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T10:59:00Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1567.8741951513823, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.05626716087649, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 27 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:59:00Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1566.3786416398286, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.65540636850494, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 25 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:03:41Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1564.6835482433685, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.452932914118634, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 30 }, { "admitted_plugins": 1, "attempted_matches": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 38, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T11:37:20Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1549.2728597100909, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.609766414462925, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:17:17Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1554.884848939414, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.6075528075571, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32 }, { "admitted_plugins": 2, "attempted_matches": 132, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 66, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 56, "max_score": null, "measured_at": "2026-07-27T11:08:00Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 132, "rating_method": "sequential_elo", "raw_elo": 1547.7029292841976, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.0280823912595, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.355146918744417, "unilateral_faults": 0, "wins": 76 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 23, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:37:21Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1559.2077630285237, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.46607244200722, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 37.61757338116737, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugins": 2, "attempted_matches": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 38, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 46, "max_score": null, "measured_at": "2026-07-27T11:24:39Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1596.2341577964626, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.161802776181965, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 50.85343826377003, "unilateral_faults": 0, "wins": 76 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 35, "max_score": null, "measured_at": "2026-07-27T11:26:11Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1538.3667950040874, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.82574174672981, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 29 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 16, "max_score": null, "measured_at": "2026-07-27T11:06:11Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1544.427991149785, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.650421679977455, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 40, "max_score": null, "measured_at": "2026-07-26T05:18:07Z", "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": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1536.7147699474256, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Minimal", "reasoning_bracket": "baseline", "reasoning_bucket": "minimal", "reasoning_bucket_label": "Minimal", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "minimal" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.4785629543956, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.300442572851765, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:07:34Z", "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": 37, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1525.8350202224913, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.32886155421666, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:03:42Z", "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": 38, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1525.7692733725237, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.12979094866205, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32 }, { "admitted_plugins": 2, "attempted_matches": 86, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 43, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 68, "max_score": null, "measured_at": "2026-07-27T11:30:33Z", "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": 39, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 86, "rating_method": "sequential_elo", "raw_elo": 1539.8264900054382, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.07016550643658, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 38.46393572312315, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:07:15Z", "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": 40, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1523.974286932912, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking field omitted", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking field omitted", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.01327090561448, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 38 }, { "admitted_plugins": 3, "attempted_matches": 210, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 105, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 110, "max_score": null, "measured_at": "2026-07-27T11:26:10Z", "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": 41, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 210, "rating_method": "sequential_elo", "raw_elo": 1519.457026192892, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.81950080868389, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 15.625289791427727, "unilateral_faults": 0, "wins": 100 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 34, "max_score": null, "measured_at": "2026-07-27T10:13:23Z", "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": 42, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1521.2856555640442, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.692122535876926, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T11:03:48Z", "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": 43, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1544.0837274481669, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.67871891237462, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 47.88193642139327, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 27, "max_score": null, "measured_at": "2026-07-27T11:09:46Z", "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": 44, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1520.9036581003338, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.646494167430816, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 35 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T08:40:46Z", "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": 45, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1530.497151230373, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 46.176411006143624, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.62023516889464, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 2, "attempted_matches": 98, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 49, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 71, "max_score": null, "measured_at": "2026-07-27T11:30:26Z", "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": 46, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 97, "rating_method": "sequential_elo", "raw_elo": 1521.802394121089, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Max", "reasoning_bracket": "intensive", "reasoning_bucket": "max", "reasoning_bucket_label": "Max", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "max" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.85469736568789, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 39.11849350131416, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:07:38Z", "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": 47, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1497.821508842899, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.157076581963906, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 36 }, { "admitted_plugins": 2, "attempted_matches": 144, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 72, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 77, "max_score": null, "measured_at": "2026-07-27T11:26:06Z", "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": 48, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 144, "rating_method": "sequential_elo", "raw_elo": 1493.3191497437815, "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-mini", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.753682456063075, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 15.036461425079892, "unilateral_faults": 0, "wins": 67 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T11:37:19Z", "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": 49, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1512.4648061510393, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.05482259085901, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.28203845127178, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 22, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:07:33Z", "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": 50, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1508.3722086805085, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.01048103554146, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 41.6303220574653, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:05:52Z", "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": 51, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1504.0748772526315, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.06115710405442, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.19324853318743, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 4, "attempted_matches": 82, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 5, "distinct_rated_opponents": 41, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 103, "max_score": null, "measured_at": "2026-07-27T11:09:40Z", "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": 52, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 82, "rating_method": "sequential_elo", "raw_elo": 1498.3592525832437, "reasoning_level": "Extended thinking (legacy shared budget)", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_exact", "request_mode": "effort", "requested_effort": "legacy_shared_thinking_budget", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Extended thinking (legacy shared budget)", "reasoning_bracket": "intensive", "reasoning_bucket": "legacy_shared_thinking_budget", "reasoning_bucket_label": "Extended thinking (legacy shared budget)", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "legacy_shared_thinking_budget" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.5856133098903, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 44.02524133296144, "unilateral_faults": 0, "wins": 83 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 23, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T11:30:34Z", "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": 53, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1489.950348493604, "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_literal_legacy", "request_mode": "effort", "requested_effort": "high", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.19349702401932, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 37.61757338116737, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 1, "attempted_matches": 74, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 37, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 40, "max_score": null, "measured_at": "2026-07-27T10:25:28Z", "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": 54, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1469.3980693923404, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.99685872000467, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 34 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T08:07:17Z", "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": 55, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1469.451876888559, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.85000638911461, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 33 }, { "admitted_plugins": 1, "attempted_matches": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 38, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 42, "max_score": null, "measured_at": "2026-07-27T11:21:01Z", "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": 56, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1459.739093474812, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.915245999404725, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 34 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 35, "max_score": null, "measured_at": "2026-07-27T11:37:19Z", "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": 57, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1479.067627271918, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.40736615648161, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 42.70587299553475, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 3, "attempted_matches": 184, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 92, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 91, "max_score": null, "measured_at": "2026-07-27T11:44:21Z", "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": 58, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 184, "rating_method": "sequential_elo", "raw_elo": 1455.8411759214753, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.84236148945967, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 19.5855325453968, "unilateral_faults": 0, "wins": 93 }, { "admitted_plugins": 2, "attempted_matches": 142, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 71, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 85, "max_score": null, "measured_at": "2026-07-27T11:08:02Z", "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": 59, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 142, "rating_method": "sequential_elo", "raw_elo": 1450.2105516399035, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.59079929471259, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 15.179828253878972, "unilateral_faults": 0, "wins": 57 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:09:47Z", "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": 60, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1469.150703841991, "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": "other", "provider_model": "cohere/north-mini-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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.36830859417666, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 41.18336395796551, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 4, "attempted_matches": 186, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 93, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 99, "max_score": null, "measured_at": "2026-07-27T11:08:01Z", "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": 61, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1459.0362386270358, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.34286812733045, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 28.80651466885331, "unilateral_faults": 0, "wins": 87 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 44, "max_score": null, "measured_at": "2026-07-26T04:30:24Z", "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": 62, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1459.640319348581, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.9743540171584, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 33.41808305530269, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T11:04:04Z", "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": 63, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1447.33708487285, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.85920360288856, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 33 }, { "admitted_plugins": 2, "attempted_matches": 72, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 36, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 69, "max_score": null, "measured_at": "2026-07-27T10:17:43Z", "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": 64, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 72, "rating_method": "sequential_elo", "raw_elo": 1463.883778294188, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.75915984031178, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 40.974394715408586, "unilateral_faults": 0, "wins": 67 }, { "admitted_plugins": 1, "attempted_matches": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 38, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T11:44:21Z", "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": 65, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1441.2006518851858, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.70088877553203, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 37 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T11:07:20Z", "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": 66, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1543.0508772303117, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.69357520783093, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 68.15703845127177, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugins": 4, "attempted_matches": 254, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 127, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 141, "max_score": null, "measured_at": "2026-07-27T11:17:17Z", "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": 67, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 254, "rating_method": "sequential_elo", "raw_elo": 1435.585169745014, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.5178295193274, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 18.59154576158009, "unilateral_faults": 0, "wins": 113 }, { "admitted_plugins": 3, "attempted_matches": 194, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 97, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 118, "max_score": null, "measured_at": "2026-07-27T11:21:00Z", "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": 68, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 194, "rating_method": "sequential_elo", "raw_elo": 1434.423428573234, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.437043207071774, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.98479089078668, "unilateral_faults": 0, "wins": 76 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 44, "max_score": null, "measured_at": "2026-07-26T01:24:50Z", "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": 69, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1443.580106809795, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.968215320622434, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 36 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:07:18Z", "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": 70, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1442.1903981687146, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.613283334610685, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 27, "max_score": null, "measured_at": "2026-07-27T10:13:57Z", "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": 71, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1435.9565657354813, "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": "omitted", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.55014764549661, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 19 }, { "admitted_plugins": 3, "attempted_matches": 172, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 86, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 95, "max_score": null, "measured_at": "2026-07-27T11:07:24Z", "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": 72, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 172, "rating_method": "sequential_elo", "raw_elo": 1427.4966669312123, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.25256072815697, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 21.721842944692018, "unilateral_faults": 0, "wins": 77 }, { "admitted_plugins": 2, "attempted_matches": 140, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 70, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 86, "max_score": null, "measured_at": "2026-07-27T11:37:21Z", "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": 73, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 140, "rating_method": "sequential_elo", "raw_elo": 1421.697875125174, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.14594446663055, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 54 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T10:28:31Z", "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": 74, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1426.356743667632, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking field omitted", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking field omitted", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.044276212350354, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T10:13:26Z", "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": 75, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1416.7106818294349, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.55024026744643, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 33 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T11:05:50Z", "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": 76, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1515.0366203285198, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "balanced", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.24533485626138, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 69.22474682633933, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:16:10Z", "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": 77, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1430.2908983914597, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.1919263578203, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T11:24:39Z", "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": 78, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1407.767805319223, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.48204243070537, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 31 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T08:38:42Z", "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": 79, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1409.8327711353909, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.31299675673494, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 40.86916081526379, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 2, "attempted_matches": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 38, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 87, "max_score": null, "measured_at": "2026-07-27T11:30:33Z", "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": 80, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1407.281846728603, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.89087169341551, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 42.09800666196841, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugins": 2, "attempted_matches": 94, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 47, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 55, "max_score": null, "measured_at": "2026-07-27T11:04:08Z", "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": 81, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 94, "rating_method": "sequential_elo", "raw_elo": 1393.1588342212412, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.50995183297395, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 28.430533588759353, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugins": 1, "attempted_matches": 74, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 37, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 48, "max_score": null, "measured_at": "2026-07-27T11:24:40Z", "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": 82, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1375.3160039220393, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.759058589728017, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3, "attempted_matches": 188, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 94, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 103, "max_score": null, "measured_at": "2026-07-27T11:21:01Z", "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": 83, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1377.3912241549654, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.52128553699262, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 19.067326122184195, "unilateral_faults": 0, "wins": 85 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-26T01:24:23Z", "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": 84, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1388.981231901262, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Max", "reasoning_bracket": "intensive", "reasoning_bucket": "max", "reasoning_bucket_label": "Max", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "max" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.446555315679618, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 14 }, { "admitted_plugins": 2, "attempted_matches": 132, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 66, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 67, "max_score": null, "measured_at": "2026-07-27T11:08:00Z", "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": 85, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 132, "rating_method": "sequential_elo", "raw_elo": 1369.477572900474, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.739636786078208, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.355146918744417, "unilateral_faults": 0, "wins": 65 }, { "admitted_plugins": 2, "attempted_matches": 132, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 66, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 78, "max_score": null, "measured_at": "2026-07-27T11:06:11Z", "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": 86, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 132, "rating_method": "sequential_elo", "raw_elo": 1366.8065500421274, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.420591696289264, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.355146918744417, "unilateral_faults": 0, "wins": 54 }, { "admitted_plugins": 1, "attempted_matches": 74, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 37, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 48, "max_score": null, "measured_at": "2026-07-27T11:07:15Z", "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": 87, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1340.6671312177457, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.62036218416104, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3, "attempted_matches": 196, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 98, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 136, "max_score": null, "measured_at": "2026-07-27T11:21:01Z", "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": 88, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 196, "rating_method": "sequential_elo", "raw_elo": 1342.0283612027545, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.419157365923827, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.792154980996397, "unilateral_faults": 0, "wins": 60 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 44, "max_score": null, "measured_at": "2026-07-27T11:07:34Z", "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": 89, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1360.9092359313067, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.238020657975618, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:06:11Z", "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": 90, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1343.9306693331305, "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": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.5579502972611, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 18 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 52, "max_score": null, "measured_at": "2026-07-26T02:19:03Z", "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": 91, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1345.5426876668148, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.25796091549614, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T11:07:33Z", "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": 92, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1321.2599404656255, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 23.893026239049423, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 27 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T11:24:44Z", "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": 93, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1306.4883081561472, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.93738491295836, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 22 }, { "admitted_plugins": 2, "attempted_matches": 140, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 70, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 98, "max_score": null, "measured_at": "2026-07-27T11:10:14Z", "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": 94, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 140, "rating_method": "sequential_elo", "raw_elo": 1301.7070258578517, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.811735212142757, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 15.606750070474943, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T11:10:14Z", "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": 95, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1305.284761574915, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 20.941820909912263, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 16 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 54, "max_score": null, "measured_at": "2026-07-27T11:30:30Z", "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": 96, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1280.5829410962074, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 16.976547721664623, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 39.80145244019624, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 54, "max_score": null, "measured_at": "2026-07-27T11:30:34Z", "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": 97, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1268.9210216510749, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 15.144663326584237, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 44.39456088374059, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 65, "max_score": null, "measured_at": "2026-07-26T02:17:58Z", "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": 98, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1243.4154165469658, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Minimal", "reasoning_bracket": "baseline", "reasoning_bucket": "minimal", "reasoning_bucket_label": "Minimal", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "minimal" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 13.059186845663168, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 15 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 51, "max_score": null, "measured_at": "2026-07-27T11:09:47Z", "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": 99, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1247.4219158546216, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 12.243419652002428, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 47.88193642139327, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 53, "max_score": null, "measured_at": "2026-07-27T11:24:40Z", "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": 100, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1123.6908903432654, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 0.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 5 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T10:46:56Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1788.705954908835, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 90.34672640532096, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 3, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-26T05:19:08Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1791.7075385947503, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 89.93824120320421, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 74 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 8, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:53:35Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1777.2678447386463, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 88.95151331383552, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 37 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T10:41:53Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1772.6067863963965, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 88.32799956129024, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 36 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 17, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1750.2486128915534, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 83.5076304126712, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 1, "attempted_matches": 50, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T10:46:50Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1732.4144195081535, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 82.67382914279403, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T11:37:21Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1710.4157199319804, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 80.58681788029159, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 37 }, { "admitted_plugins": 2, "attempted_matches": 128, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 64, "draws": 14, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 36, "max_score": null, "measured_at": "2026-07-27T10:41:50Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 128, "rating_method": "sequential_elo", "raw_elo": 1704.3788148815706, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 79.77925593934339, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 78 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:46:35Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1703.812816431412, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 79.37424207225958, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 38 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 3, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 16, "max_score": null, "measured_at": "2026-07-27T11:46:32Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1701.9160659633524, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 78.99935188287517, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 37 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 5, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:46:17Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1691.0689393099397, "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-nano", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 77.54832249268348, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:52:51Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1681.0254506469776, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 76.32595670280091, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 36 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:45:56Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1674.4080128967423, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 75.31957614668558, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 29 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 13, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:37:21Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1674.3560486853933, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 75.31262484978316, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T11:52:34Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1666.5668321788196, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 74.39181497022835, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 40 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T10:44:49Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1667.5084391584408, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 74.1340312841928, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T10:44:46Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1646.4648905020276, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 71.02490499954271, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 78, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 39, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T11:53:51Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 78, "rating_method": "sequential_elo", "raw_elo": 1632.355051545612, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 70.76130982029495, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 49 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:52:23Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1628.545670896392, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 69.18453151488029, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 35 }, { "admitted_plugins": 2, "attempted_matches": 72, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 36, "draws": 12, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 35, "max_score": null, "measured_at": "2026-07-27T11:46:19Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 72, "rating_method": "sequential_elo", "raw_elo": 1644.4298779060618, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Max", "reasoning_bracket": "intensive", "reasoning_bucket": "max", "reasoning_bucket_label": "Max", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "max" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 69.03024505442248, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 43.7735813706023, "unilateral_faults": 0, "wins": 81 }, { "admitted_plugins": 2, "attempted_matches": 80, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 40, "draws": 10, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T10:41:40Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1634.4148964003216, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 68.70041680687149, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 44 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-27T11:37:08Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1623.151639774578, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 68.3352570412757, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 31 }, { "admitted_plugins": 2, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 31, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 27, "max_score": null, "measured_at": "2026-07-27T11:36:38Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1628.3092646305531, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "balanced", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 67.21194886050958, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 40.6135880525129, "unilateral_faults": 0, "wins": 66 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 8, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:53:34Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1625.9638890170804, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 66.37931618441283, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 45.462269258808135, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugins": 2, "attempted_matches": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 38, "draws": 8, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1610.797508914191, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 65.37732935727273, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 35.86719719448568, "unilateral_faults": 0, "wins": 70 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:44:32Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1591.7478127385095, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 64.38321088344401, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-26T02:17:56Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1597.3872665406357, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Minimal", "reasoning_bracket": "baseline", "reasoning_bucket": "minimal", "reasoning_bucket_label": "Minimal", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "minimal" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 63.74719915833959, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 48 }, { "admitted_plugins": 1, "attempted_matches": 42, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 21, "draws": 5, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T11:53:48Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1589.6396414098424, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 62.019294143192774, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 40.79847712741413, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugins": 3, "attempted_matches": 200, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 100, "draws": 22, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 80, "max_score": null, "measured_at": "2026-07-27T11:30:11Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 200, "rating_method": "sequential_elo", "raw_elo": 1565.809397581451, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 61.32306059649945, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.516513567803994, "unilateral_faults": 0, "wins": 98 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 27, "draws": 3, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-27T11:46:17Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1579.6136430974516, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 60.76783956869306, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 39.95999312316211, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 4, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T11:52:38Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1555.945264596268, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 59.81864880409941, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32 }, { "admitted_plugins": 3, "attempted_matches": 178, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 89, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 74, "max_score": null, "measured_at": "2026-07-27T11:52:32Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 178, "rating_method": "sequential_elo", "raw_elo": 1551.392329535351, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 59.05974856700104, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 20.644329938565026, "unilateral_faults": 0, "wins": 102 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T10:41:09Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1566.8929275335172, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 58.39911627396981, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.19324853318743, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:52:51Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1560.571039169908, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.85138882139616, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 43.40903824311957, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 2, "attempted_matches": 120, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 60, "draws": 5, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 50, "max_score": null, "measured_at": "2026-07-27T11:44:32Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 120, "rating_method": "sequential_elo", "raw_elo": 1539.3980095984984, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.47045192344825, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 20.50235421223841, "unilateral_faults": 0, "wins": 65 }, { "admitted_plugins": 2, "attempted_matches": 118, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 59, "draws": 8, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 55, "max_score": null, "measured_at": "2026-07-27T11:46:33Z", "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": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 118, "rating_method": "sequential_elo", "raw_elo": 1538.1474467950384, "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-mini", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.264851725461014, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 20.8603483440617, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 10, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:36:33Z", "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": 37, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1533.5565018760735, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 56.714061176471255, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 4, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 16, "max_score": null, "measured_at": "2026-07-26T01:20:52Z", "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": 38, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1536.7350100578335, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Max", "reasoning_bracket": "intensive", "reasoning_bucket": "max", "reasoning_bucket_label": "Max", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "max" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.633695043376434, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 20 }, { "admitted_plugins": 3, "attempted_matches": 138, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 69, "draws": 13, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 107, "max_score": null, "measured_at": "2026-07-27T11:53:35Z", "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": 39, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 138, "rating_method": "sequential_elo", "raw_elo": 1536.0930490675153, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.39378555896641, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 35.776224893619634, "unilateral_faults": 0, "wins": 118 }, { "admitted_plugins": 1, "attempted_matches": 82, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 41, "draws": 10, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-27T11:46:35Z", "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": 40, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 82, "rating_method": "sequential_elo", "raw_elo": 1510.098396671887, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 54.55378800839192, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 39 }, { "admitted_plugins": 4, "attempted_matches": 242, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 121, "draws": 17, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 120, "max_score": null, "measured_at": "2026-07-27T11:30:20Z", "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": 41, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 242, "rating_method": "sequential_elo", "raw_elo": 1516.80550194545, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 54.484864054652334, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 20.16006027106505, "unilateral_faults": 0, "wins": 105 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-26T04:34:09Z", "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": 42, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1523.1683060416635, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.91719217050105, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 33.41808305530269, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:36:38Z", "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": 43, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1516.5320737959407, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.48135378529035, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 38.53975118769762, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugins": 2, "attempted_matches": 130, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 65, "draws": 12, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 65, "max_score": null, "measured_at": "2026-07-27T10:41:44Z", "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": 44, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 130, "rating_method": "sequential_elo", "raw_elo": 1499.236810439388, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.38713921457689, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.801044736378422, "unilateral_faults": 0, "wins": 53 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T10:40:00Z", "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": 45, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1508.2219156109704, "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": "omitted", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.81947406397143, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 18 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:36:36Z", "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": 46, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1498.859087874097, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.70853629281069, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 22 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 3, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:36:11Z", "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": 47, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1494.5099950724373, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking field omitted", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking field omitted", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.49077663608371, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T10:46:50Z", "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": 48, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1496.011348653353, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.455302113536305, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T10:38:33Z", "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": 49, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1502.9248303375296, "reasoning_level": "Highest", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": null, "requested_effort": "highest", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Highest", "reasoning_bracket": "intensive", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.110878446006915, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 16 }, { "admitted_plugins": 1, "attempted_matches": 42, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 21, "draws": 8, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 16, "max_score": null, "measured_at": "2026-07-27T10:36:17Z", "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": 50, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1498.497941533217, "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": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.71534315686365, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 18 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 4, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 41, "max_score": null, "measured_at": "2026-07-26T03:28:35Z", "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": 51, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1495.4573766623844, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.21027749681558, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 33.41808305530269, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 3, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:52:58Z", "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": 52, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1480.3349355924784, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.00396058789727, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 33 }, { "admitted_plugins": 4, "attempted_matches": 86, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 5, "distinct_rated_opponents": 43, "draws": 20, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 73, "max_score": null, "measured_at": "2026-07-27T11:36:36Z", "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": 53, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 86, "rating_method": "sequential_elo", "raw_elo": 1501.641835768445, "reasoning_level": "Extended thinking (legacy shared budget)", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_exact", "request_mode": "effort", "requested_effort": "legacy_shared_thinking_budget", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Extended thinking (legacy shared budget)", "reasoning_bracket": "intensive", "reasoning_bucket": "legacy_shared_thinking_budget", "reasoning_bucket_label": "Extended thinking (legacy shared budget)", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "legacy_shared_thinking_budget" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.67604159099529, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.43862771637128, "unilateral_faults": 0, "wins": 79 }, { "admitted_plugins": 2, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 34, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 50, "max_score": null, "measured_at": "2026-07-27T11:44:21Z", "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": 54, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1527.6744919780415, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.44356696704924, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 53.9669329725016, "unilateral_faults": 0, "wins": 51 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 10, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 27, "max_score": null, "measured_at": "2026-07-27T11:37:12Z", "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": 55, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1486.847787377084, "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_literal_legacy", "request_mode": "effort", "requested_effort": "high", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.39619884773006, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 39.60745956276516, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 3, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 81, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 84, "max_score": null, "measured_at": "2026-07-27T11:52:36Z", "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": 56, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1466.9886937713543, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.43562893658869, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 23.759481979378876, "unilateral_faults": 0, "wins": 78 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T11:52:32Z", "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": 57, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1467.99966969457, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.15146009630666, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 34, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 58, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1455.789381704686, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking field omitted", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking field omitted", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 46.195935526761325, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 23 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T08:28:44Z", "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": 59, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1452.7547853739904, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.905146597643856, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:52:58Z", "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": 60, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1448.0809451241314, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.16477138641322, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 1, "attempted_matches": 35, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 4, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-27T11:37:14Z", "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": 61, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 35, "rating_method": "sequential_elo", "raw_elo": 1460.076493018715, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.47139940280178, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 42.817992173360395, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 4, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 81, "draws": 13, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 86, "max_score": null, "measured_at": "2026-07-27T10:41:53Z", "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": 62, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1441.9272292669764, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.00034064191036, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 33.87748199980286, "unilateral_faults": 0, "wins": 63 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:43:04Z", "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": 63, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1429.7879988349669, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.33396509337835, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T10:38:32Z", "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": 64, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1418.0209855099072, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.47292470469752, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 25 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 34, "max_score": null, "measured_at": "2026-07-27T11:53:51Z", "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": 65, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1417.6969290178033, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.325050962101, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 1, "attempted_matches": 84, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 42, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 49, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 66, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 84, "rating_method": "sequential_elo", "raw_elo": 1408.9987545376268, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.09911159247618, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T10:39:35Z", "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": 67, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1430.7493983829115, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.89186947333852, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 39.60745956276516, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 2, "attempted_matches": 122, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 61, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 69, "max_score": null, "measured_at": "2026-07-27T10:40:04Z", "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": 68, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 122, "rating_method": "sequential_elo", "raw_elo": 1409.7666921541868, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.2094045434509, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 19.7562594006596, "unilateral_faults": 0, "wins": 51 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T10:38:30Z", "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": 69, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1420.038975375964, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.02316688669191, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 20 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T11:46:13Z", "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": 70, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1424.6190995091226, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.445251848942995, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 45.462269258808135, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 3, "attempted_matches": 186, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 93, "draws": 8, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 94, "max_score": null, "measured_at": "2026-07-27T11:52:36Z", "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": 71, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1402.4748118054893, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.26711538483674, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 19.446476867543144, "unilateral_faults": 0, "wins": 84 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T10:38:34Z", "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": 72, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1400.355913354061, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.65939289391045, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 24 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-27T10:43:06Z", "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": 73, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1388.4103550666105, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.933715039786, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 20 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 17, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:44:14Z", "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": 74, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1395.505080795559, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.05328535902041, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 34, "max_score": null, "measured_at": "2026-07-27T10:44:43Z", "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": 75, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1369.2947045902554, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.37659816081083, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 19 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 3, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 35, "max_score": null, "measured_at": "2026-07-27T10:44:50Z", "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": 76, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1384.079848744715, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.615449335199195, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 49.26384793916254, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T10:43:03Z", "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": 77, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1381.5813863174303, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.46194565997123, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 47.5751600509567, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 78, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1357.4859927674747, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.27058263129217, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 23 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 35, "max_score": null, "measured_at": "2026-07-27T10:36:18Z", "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": 79, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1356.7474097662753, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.17178175285869, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 27 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T10:46:50Z", "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": 80, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1379.3228938160337, "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": "other", "provider_model": "cohere/north-mini-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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.15982519048976, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 47.5751600509567, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T08:28:47Z", "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": 81, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1365.0587937088449, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.66842106080365, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 15 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:44:23Z", "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": 82, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1354.7769806450185, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.299677169988506, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 10, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 47, "max_score": null, "measured_at": "2026-07-26T02:16:28Z", "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": 83, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1362.173682387377, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Minimal", "reasoning_bracket": "baseline", "reasoning_bucket": "minimal", "reasoning_bucket_label": "Minimal", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "minimal" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.28247725695701, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 23 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 44, "max_score": null, "measured_at": "2026-07-27T11:44:24Z", "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": 84, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1347.1351283730276, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.776314936759203, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-27T10:38:38Z", "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": 85, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1345.003199893997, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.60074877484011, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 27 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T10:44:46Z", "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": 86, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1362.877850832631, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.529723961553977, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 42.25107233303306, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T10:43:01Z", "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": 87, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1364.522971792873, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.999309214021817, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 49.26384793916254, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 40, "max_score": null, "measured_at": "2026-07-27T11:44:17Z", "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": 88, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1338.9971736131567, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.7973175132515, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 20 }, { "admitted_plugins": 2, "attempted_matches": 124, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 62, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 87, "max_score": null, "measured_at": "2026-07-27T11:53:45Z", "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": 89, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 124, "rating_method": "sequential_elo", "raw_elo": 1334.7200708029854, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.214944656619977, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 19.33958883428227, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 53, "max_score": null, "measured_at": "2026-07-26T02:18:39Z", "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": 90, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1343.802645127367, "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": true, "evidence_status": "retained_exact", "request_mode": "toggle", "requested_effort": "enabled", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.824967923441967, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 5, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:52:31Z", "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": 91, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1331.884389148848, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.736210534597397, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 23 }, { "admitted_plugins": 1, "attempted_matches": 35, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 50, "max_score": null, "measured_at": "2026-07-27T11:53:48Z", "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": 92, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 35, "rating_method": "sequential_elo", "raw_elo": 1346.3039086212673, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.658776025462103, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 39.016413493006, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-26T02:14:14Z", "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": 93, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1337.3836752186996, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.966296840321345, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 13 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 45, "max_score": null, "measured_at": "2026-07-27T10:45:10Z", "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": 94, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1338.0261125347924, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.364274717844992, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 2, "attempted_matches": 82, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 41, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 52, "max_score": null, "measured_at": "2026-07-27T10:41:39Z", "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": 95, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 82, "rating_method": "sequential_elo", "raw_elo": 1331.1083724223636, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.225170931660724, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 33.41808305530269, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 54, "max_score": null, "measured_at": "2026-07-27T10:45:13Z", "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": 96, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1332.7686768658657, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.004963816593825, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 37.551153208577354, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 2, "attempted_matches": 106, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 53, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 72, "max_score": null, "measured_at": "2026-07-27T11:52:32Z", "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": 97, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 106, "rating_method": "sequential_elo", "raw_elo": 1292.7620567863044, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.06381411034904, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.370311027326338, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugins": 2, "attempted_matches": 124, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 62, "draws": 3, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 92, "max_score": null, "measured_at": "2026-07-27T10:41:56Z", "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": 98, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 124, "rating_method": "sequential_elo", "raw_elo": 1247.794253674446, "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": true, "evidence_status": "retained_exact", "request_mode": "toggle", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 18.594475422927697, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 29 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 45, "max_score": null, "measured_at": "2026-07-27T11:52:33Z", "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": 99, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1184.250882263081, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 9.62312811760228, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 40, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-26T05:16:44Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1908.3795775583417, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 99.7174091533898, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 39 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T11:07:53Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1839.8110785855636, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 92.43903356479711, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 58 }, { "admitted_plugins": 2, "attempted_matches": 106, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 53, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T10:36:03Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 106, "rating_method": "sequential_elo", "raw_elo": 1831.0772363583328, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 90.66753720750904, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.30013411033436, "unilateral_faults": 0, "wins": 82 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T11:06:02Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1810.7420076245985, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 88.73890042665397, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 58 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T10:30:49Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1741.5924576205412, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 78.91131680197287, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T11:36:21Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1730.8896425336536, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 78.20945134532496, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 42 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:09:44Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1721.3733595723618, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 76.52631679447857, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 41 }, { "admitted_plugins": 2, "attempted_matches": 74, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 37, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T11:36:24Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1716.6223916896186, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 74.68590448880083, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 34.14738066126455, "unilateral_faults": 0, "wins": 96 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:03:55Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1690.141060653709, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 72.98349769903467, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 42 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T11:36:22Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1657.169899748788, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 68.47656737578293, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 42 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:05:51Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1655.5878327465305, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 67.93204374088673, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 37 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T11:09:45Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1667.5150915775343, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 67.56797718896486, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 40.86916081526379, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugins": 3, "attempted_matches": 206, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 102, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 76, "max_score": null, "measured_at": "2026-07-27T11:09:46Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 206, "rating_method": "sequential_elo", "raw_elo": 1638.8693146453372, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 66.36171022225238, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 16.603769221136574, "unilateral_faults": 0, "wins": 130 }, { "admitted_plugins": 2, "attempted_matches": 126, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 63, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 50, "max_score": null, "measured_at": "2026-07-27T11:04:00Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 126, "rating_method": "sequential_elo", "raw_elo": 1640.1550052348434, "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-mini", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 66.30476749736133, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 18.755723064737715, "unilateral_faults": 0, "wins": 76 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 27, "max_score": null, "measured_at": "2026-07-26T05:17:45Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1648.2434811975372, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Minimal", "reasoning_bracket": "baseline", "reasoning_bucket": "minimal", "reasoning_bucket_label": "Minimal", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "minimal" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 66.08096329718745, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 31.007726186437235, "unilateral_faults": 0, "wins": 61 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T11:05:48Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1637.762905975935, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 65.72170653066799, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:36:23Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1636.5407743062012, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 65.31899895038302, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 33 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:04:00Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1626.8615300978795, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 64.05449486122448, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 33 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T10:59:24Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1620.9004693099198, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 63.275737183469275, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 34 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T08:36:03Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1613.924246727442, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 62.60740530517968, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 33 }, { "admitted_plugins": 3, "attempted_matches": 128, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 64, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 51, "max_score": null, "measured_at": "2026-07-27T11:55:02Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 128, "rating_method": "sequential_elo", "raw_elo": 1615.0897353689145, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 61.653545677315115, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 31.928056527532547, "unilateral_faults": 0, "wins": 77 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T10:53:24Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1604.4884389644276, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 61.59421983387494, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 37 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 36, "max_score": null, "measured_at": "2026-07-27T11:07:53Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1591.3212202571904, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 60.25603724598094, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 34 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:54:26Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1585.6437673215585, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking field omitted", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking field omitted", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 59.132337083693706, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 37 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-26T05:19:02Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1594.7046977870536, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Minimal", "reasoning_bracket": "baseline", "reasoning_bucket": "minimal", "reasoning_bucket_label": "Minimal", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "minimal" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 59.08661445196189, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 31.007726186437235, "unilateral_faults": 0, "wins": 51 }, { "admitted_plugins": 3, "attempted_matches": 118, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 59, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 97, "max_score": null, "measured_at": "2026-07-27T11:03:59Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 118, "rating_method": "sequential_elo", "raw_elo": 1597.4696635584298, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 58.8726488028644, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 36.51120413268083, "unilateral_faults": 0, "wins": 131 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:30:07Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1573.8998861000514, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.49104851229338, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 29 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:05:45Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1571.1643984055847, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.44029280728862, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 41 }, { "admitted_plugins": 3, "attempted_matches": 214, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 107, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 92, "max_score": null, "measured_at": "2026-07-27T11:07:52Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 214, "rating_method": "sequential_elo", "raw_elo": 1569.051457384776, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.37331813393658, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 15.334374414189384, "unilateral_faults": 0, "wins": 122 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T10:15:39Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1563.3796006203124, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 56.004212916192515, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 34 }, { "admitted_plugins": 2, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 34, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 44, "max_score": null, "measured_at": "2026-07-27T11:05:45Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1573.87579650109, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "balanced", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.562434490225975, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 38.69173419161021, "unilateral_faults": 0, "wins": 64 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 34, "max_score": null, "measured_at": "2026-07-27T10:53:27Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1574.402889663777, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.37088757570538, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 41.18336395796551, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T11:54:22Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1563.6722330880127, "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": "omitted", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.05572388516481, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 1, "attempted_matches": 78, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 39, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:07:55Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 78, "rating_method": "sequential_elo", "raw_elo": 1544.0623728482103, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 54.40449302982698, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 50 }, { "admitted_plugins": 2, "attempted_matches": 134, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 67, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 67, "max_score": null, "measured_at": "2026-07-27T11:54:26Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 134, "rating_method": "sequential_elo", "raw_elo": 1541.7067569374103, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.638525271468005, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 67 }, { "admitted_plugins": 3, "attempted_matches": 134, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 67, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 61, "max_score": null, "measured_at": "2026-07-27T11:55:02Z", "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": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 134, "rating_method": "sequential_elo", "raw_elo": 1551.187140315273, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.48050971680028, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.25123141631108, "unilateral_faults": 0, "wins": 73 }, { "admitted_plugins": 3, "attempted_matches": 140, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 70, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 109, "max_score": null, "measured_at": "2026-07-27T11:54:18Z", "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": 37, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 140, "rating_method": "sequential_elo", "raw_elo": 1552.2221681288854, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Max", "reasoning_bracket": "intensive", "reasoning_bucket": "max", "reasoning_bucket_label": "Max", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "max" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.439927382671186, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 31.933316946790622, "unilateral_faults": 0, "wins": 149 }, { "admitted_plugins": 2, "attempted_matches": 130, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 65, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 63, "max_score": null, "measured_at": "2026-07-27T11:31:22Z", "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": 38, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 130, "rating_method": "sequential_elo", "raw_elo": 1540.3330460767777, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.3592866591907, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.8435026888779, "unilateral_faults": 0, "wins": 67 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T11:09:46Z", "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": 39, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1537.8619196179889, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.99215754691314, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 34 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 23, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T11:54:22Z", "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": 40, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1544.5012678250691, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.23449928003549, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 33.815994700812965, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugins": 2, "attempted_matches": 124, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 62, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 62, "max_score": null, "measured_at": "2026-07-27T10:59:20Z", "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": 41, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 124, "rating_method": "sequential_elo", "raw_elo": 1514.7809634969965, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.87227457080003, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 62 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T11:38:26Z", "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": 42, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1502.494574211802, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.65165422462213, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:37:27Z", "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": 43, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1507.216526715812, "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": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.68030592612551, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-27T08:38:34Z", "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": 44, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1496.914059374072, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.433559455600474, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 27 }, { "admitted_plugins": 2, "attempted_matches": 128, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 64, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 71, "max_score": null, "measured_at": "2026-07-27T11:06:05Z", "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": 45, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 128, "rating_method": "sequential_elo", "raw_elo": 1494.0376407858523, "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-nano", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.26461648443617, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 18.289400506511907, "unilateral_faults": 0, "wins": 57 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T11:17:13Z", "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": 46, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1486.9450008445583, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 46.43780435774322, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 36 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:24:42Z", "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": 47, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1484.101949958685, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking field omitted", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking field omitted", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.759775387566016, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 29 }, { "admitted_plugins": 3, "attempted_matches": 189, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 95, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 104, "max_score": null, "measured_at": "2026-07-27T11:17:08Z", "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": 48, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1482.0610924621042, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.63424487271845, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 18.91847187152537, "unilateral_faults": 0, "wins": 85 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 35, "max_score": null, "measured_at": "2026-07-27T11:03:45Z", "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": 49, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1498.1567772201045, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.57473728904729, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 39.60745956276516, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 45, "max_score": null, "measured_at": "2026-07-26T02:17:20Z", "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": 50, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1488.6688151212495, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.886064479879934, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 35 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T10:59:03Z", "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": 51, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1498.1236759239546, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.83748928548472, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.62023516889464, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 4, "attempted_matches": 80, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 5, "distinct_rated_opponents": 40, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 89, "max_score": null, "measured_at": "2026-07-27T11:38:30Z", "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": 52, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1507.2833658293985, "reasoning_level": "Extended thinking (legacy shared budget)", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_exact", "request_mode": "effort", "requested_effort": "legacy_shared_thinking_budget", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Extended thinking (legacy shared budget)", "reasoning_bracket": "intensive", "reasoning_bucket": "legacy_shared_thinking_budget", "reasoning_bucket_label": "Extended thinking (legacy shared budget)", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "legacy_shared_thinking_budget" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.52306535616138, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 45.10696581322496, "unilateral_faults": 0, "wins": 89 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T11:17:08Z", "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": 53, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1476.3023229705768, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.38532142418434, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 2, "attempted_matches": 136, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 68, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 56, "max_score": null, "measured_at": "2026-07-27T11:37:40Z", "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": 54, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 136, "rating_method": "sequential_elo", "raw_elo": 1470.4484547993857, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.37390326134637, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 16.461902543922633, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 41, "max_score": null, "measured_at": "2026-07-27T11:26:19Z", "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": 55, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1482.226825234452, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.82956786001692, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 36.39318729849085, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-27T11:09:43Z", "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": 56, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1481.7615272516564, "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": "other", "provider_model": "cohere/north-mini-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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.997436567986185, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 43.7735813706023, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 45, "max_score": null, "measured_at": "2026-07-26T01:23:46Z", "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": 57, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1473.4501921154751, "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": true, "evidence_status": "retained_exact", "request_mode": "toggle", "requested_effort": "enabled", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.89789158042775, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 35 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T07:48:11Z", "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": 58, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1456.9711745696457, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.21538951578612, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32 }, { "admitted_plugins": 2, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 63, "max_score": null, "measured_at": "2026-07-27T11:05:53Z", "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": 59, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1463.9651854578856, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.65095770356271, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 43.979783736733566, "unilateral_faults": 0, "wins": 63 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 22, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 36, "max_score": null, "measured_at": "2026-07-27T10:59:03Z", "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": 60, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1460.0772374862684, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.56507075019223, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 39.941634169259466, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T08:07:41Z", "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": 61, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1454.3672812155585, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.24214147038237, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 45.462269258808135, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugins": 2, "attempted_matches": 86, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 43, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 57, "max_score": null, "measured_at": "2026-07-27T11:26:19Z", "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": 62, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 86, "rating_method": "sequential_elo", "raw_elo": 1440.1690757297024, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.83162319473614, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 31.642442208147656, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 3, "attempted_matches": 196, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 98, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 109, "max_score": null, "measured_at": "2026-07-27T11:36:24Z", "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": 63, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 196, "rating_method": "sequential_elo", "raw_elo": 1428.0841806139645, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.6894460221831, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.89670599806736, "unilateral_faults": 0, "wins": 87 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 35, "max_score": null, "measured_at": "2026-07-27T10:17:46Z", "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": 64, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1449.4234555848543, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.65174334487914, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 44.9315472806888, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugins": 2, "attempted_matches": 130, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 65, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 68, "max_score": null, "measured_at": "2026-07-27T11:18:25Z", "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": 65, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 130, "rating_method": "sequential_elo", "raw_elo": 1426.8494348714175, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.538135675658424, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.801044736378422, "unilateral_faults": 0, "wins": 62 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T11:24:42Z", "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": 66, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1427.2591466449226, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.33378677910713, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 30 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T11:30:08Z", "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": 67, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1424.7213899013211, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.889795026123, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 2, "attempted_matches": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 38, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 64, "max_score": null, "measured_at": "2026-07-27T11:36:22Z", "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": 68, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1475.770927184747, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.591336171666406, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 51.78081388532118, "unilateral_faults": 0, "wins": 54 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 50, "max_score": null, "measured_at": "2026-07-27T11:03:53Z", "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": 69, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1433.6870639522708, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.38497422902105, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 37.38178527761111, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:36:22Z", "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": 70, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1426.1484616915282, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.25705460545867, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 22 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T10:59:17Z", "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": 71, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1412.1255644657329, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.6633342427911, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 27 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T10:37:45Z", "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": 72, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1460.8792605596052, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.62676198026428, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 67.16844047215152, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 27, "max_score": null, "measured_at": "2026-07-26T23:00:21Z", "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": 73, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1416.8015449056545, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.612092900151, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 27 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 40, "max_score": null, "measured_at": "2026-07-27T11:06:04Z", "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": 74, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1422.872779287951, "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_literal_legacy", "request_mode": "effort", "requested_effort": "high", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.574874573353014, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 41.18336395796551, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 2, "attempted_matches": 132, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 66, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 76, "max_score": null, "measured_at": "2026-07-27T11:30:00Z", "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": 75, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 132, "rating_method": "sequential_elo", "raw_elo": 1402.083848243849, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.29726259726838, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.85345304153558, "unilateral_faults": 0, "wins": 56 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 40, "max_score": null, "measured_at": "2026-07-27T11:03:58Z", "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": 76, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1419.3250538494135, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.57852104475718, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.28203845127178, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:30:08Z", "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": 77, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1394.6909165849377, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.07904754522137, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 27, "max_score": null, "measured_at": "2026-07-26T02:15:57Z", "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": 78, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1392.94803374959, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Max", "reasoning_bracket": "intensive", "reasoning_bucket": "max", "reasoning_bucket_label": "Max", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "max" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.381026187959016, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 13 }, { "admitted_plugins": 2, "attempted_matches": 126, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 63, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 76, "max_score": null, "measured_at": "2026-07-27T11:36:24Z", "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": 79, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 126, "rating_method": "sequential_elo", "raw_elo": 1378.8097448915178, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.157624044502754, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 18.8015810723003, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 43, "max_score": null, "measured_at": "2026-07-27T11:06:06Z", "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": 80, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1379.5223503800132, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.91154038722549, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 41.18336395796551, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 42, "max_score": null, "measured_at": "2026-07-27T10:15:58Z", "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": 81, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1358.1292477360432, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.609212884277255, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 18, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T11:30:07Z", "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": 82, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1369.5464379088992, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.89400329893377, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 47, "max_score": null, "measured_at": "2026-07-27T11:07:52Z", "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": 83, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1370.1870771688791, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.69197294013675, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 41.18336395796551, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 36, "max_score": null, "measured_at": "2026-07-27T10:13:26Z", "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": 84, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1349.90531693581, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.115764310136107, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 22 }, { "admitted_plugins": 2, "attempted_matches": 130, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 63, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 90, "max_score": null, "measured_at": "2026-07-27T11:36:23Z", "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": 85, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 130, "rating_method": "sequential_elo", "raw_elo": 1339.7266305359385, "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": "other", "provider_model": "cohere/north-mini-code", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.1563438776522, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.801044736378422, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 41, "max_score": null, "measured_at": "2026-07-27T11:07:27Z", "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": 86, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1355.5092833564145, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.80729258947612, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 40.86916081526379, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-26T02:18:59Z", "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": 87, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1340.532812293546, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.53346036165865, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 10 }, { "admitted_plugins": 4, "attempted_matches": 233, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 117, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 175, "max_score": null, "measured_at": "2026-07-27T11:38:30Z", "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": 88, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 233, "rating_method": "sequential_elo", "raw_elo": 1304.2443438279372, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.14962114886749, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 21.353618598248712, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugins": 3, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 90, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 125, "max_score": null, "measured_at": "2026-07-27T11:36:24Z", "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": 89, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1297.2587401740643, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.382657975617843, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 19.960087583821387, "unilateral_faults": 0, "wins": 57 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 34, "max_score": null, "measured_at": "2026-07-27T10:36:04Z", "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": 90, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1301.0437601099366, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 20.745733263714285, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 36, "max_score": null, "measured_at": "2026-07-27T11:30:07Z", "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": 91, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1272.023445307137, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 18.05367245403799, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 24 }, { "admitted_plugins": 2, "attempted_matches": 126, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 63, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 77, "max_score": null, "measured_at": "2026-07-27T10:30:43Z", "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": 92, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 126, "rating_method": "sequential_elo", "raw_elo": 1264.8881004574012, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 17.279603403559378, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 18.755723064737715, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 59, "max_score": null, "measured_at": "2026-07-27T11:07:55Z", "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": 93, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1262.971405382954, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 14.82966031579288, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 39.80145244019624, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 46, "max_score": null, "measured_at": "2026-07-27T11:36:23Z", "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": 94, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1245.2596467020408, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 14.557228718434729, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 14 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 46, "max_score": null, "measured_at": "2026-07-27T11:17:13Z", "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": 95, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1176.6504298057089, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 5.363284090316728, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 10 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 45, "max_score": null, "measured_at": "2026-07-27T11:09:47Z", "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": 96, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1172.4066172061932, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 5.146710224123554, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 17 }, { "admitted_plugins": 1, "attempted_matches": 42, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 21, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T10:36:04Z", "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": 97, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1143.6148913795123, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 0.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T11:07:56Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1910.1404215986424, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 61 }, { "admitted_plugins": 3, "attempted_matches": 186, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 93, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T10:46:49Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1814.1521582571097, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 84.85770377828395, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 19.53054898057647, "unilateral_faults": 0, "wins": 153 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T10:50:04Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1742.3401615411974, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 73.64139541154456, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 48 }, { "admitted_plugins": 2, "attempted_matches": 116, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 58, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 40, "max_score": null, "measured_at": "2026-07-27T11:04:07Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 116, "rating_method": "sequential_elo", "raw_elo": 1730.1736010828918, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 71.62324112334503, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 76 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 9, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 16, "max_score": null, "measured_at": "2026-07-27T11:06:02Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1686.9133200163933, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 65.52897413963234, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 43 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T11:03:50Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1683.6684140637717, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 64.91576179922941, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 46 }, { "admitted_plugins": 2, "attempted_matches": 72, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 36, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:44:35Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 72, "rating_method": "sequential_elo", "raw_elo": 1697.0145305689157, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 64.68307799655075, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 35.894862185116764, "unilateral_faults": 0, "wins": 86 }, { "admitted_plugins": 3, "attempted_matches": 114, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 57, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 55, "max_score": null, "measured_at": "2026-07-27T11:07:56Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 114, "rating_method": "sequential_elo", "raw_elo": 1692.99759374344, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 63.7778049142926, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 38.178218158143345, "unilateral_faults": 0, "wins": 165 }, { "admitted_plugins": 2, "attempted_matches": 80, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 40, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-26T05:18:46Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1686.0665086802464, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 63.18013490216033, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 54 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 5, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 5, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T10:59:35Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1672.1128256209613, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 62.628672220103525, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 38 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T10:44:31Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1649.3609751746642, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking field omitted", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking field omitted", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 59.81731792757247, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 49 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T11:18:24Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1637.7826189897944, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.91782061761204, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 29 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 6, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T10:59:39Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1636.0494722351684, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking field omitted", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking field omitted", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.75514722037097, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 45 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T11:04:07Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1602.2012432700476, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.51149993427681, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32 }, { "admitted_plugins": 2, "attempted_matches": 72, "capped_draws": 11, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 36, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:44:26Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 72, "rating_method": "sequential_elo", "raw_elo": 1627.714306163753, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.69099122402372, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 52.34956811791491, "unilateral_faults": 0, "wins": 84 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 13, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-26T05:11:55Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1606.890781954458, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.35463436894605, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T11:03:56Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1611.591302525787, "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_literal_legacy", "request_mode": "effort", "requested_effort": "high", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.26533615379074, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 37.38178527761111, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T09:25:52Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1564.7574379284083, "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.85724479955294, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 31 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 5, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 5, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T10:59:36Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1548.0692879399865, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.793641641644086, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 31 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 9, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T08:14:34Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1541.4118035776828, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.877873486874975, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 25, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 25, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T11:44:43Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1541.4688058948389, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.65007148744865, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 15 }, { "admitted_plugins": 3, "attempted_matches": 212, "capped_draws": 103, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 106, "draws": 103, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 44, "max_score": null, "measured_at": "2026-07-27T11:07:56Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 212, "rating_method": "sequential_elo", "raw_elo": 1537.8079299083918, "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-nano", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.56690883616381, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 15.33901212384661, "unilateral_faults": 0, "wins": 65 }, { "admitted_plugins": 3, "attempted_matches": 132, "capped_draws": 40, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 66, "draws": 40, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T11:18:24Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 132, "rating_method": "sequential_elo", "raw_elo": 1536.5996659469154, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.46538459256074, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 15, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T09:17:43Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1524.6754320667146, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.39565736475438, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1, "attempted_matches": 30, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 5, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T10:41:07Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1544.324469670316, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.76998981781314, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 5, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 5, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T10:44:32Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1522.545055470742, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.45816504693588, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32 }, { "admitted_plugins": 3, "attempted_matches": 188, "capped_draws": 93, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 94, "draws": 93, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 48, "max_score": null, "measured_at": "2026-07-27T11:44:47Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1511.3185496845665, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.01038466859352, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 18.993268825260195, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-27T10:52:42Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1499.683273236858, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.413437929557105, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-26T05:18:58Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1506.0213602790975, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.50824142419229, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 32.561240097148016, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 4, "attempted_matches": 96, "capped_draws": 28, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 5, "distinct_rated_opponents": 48, "draws": 46, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 85, "max_score": null, "measured_at": "2026-07-27T11:06:03Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 96, "rating_method": "sequential_elo", "raw_elo": 1515.396977372414, "reasoning_level": "Extended thinking (legacy shared budget)", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_exact", "request_mode": "effort", "requested_effort": "legacy_shared_thinking_budget", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Extended thinking (legacy shared budget)", "reasoning_bracket": "intensive", "reasoning_bucket": "legacy_shared_thinking_budget", "reasoning_bucket_label": "Extended thinking (legacy shared budget)", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "legacy_shared_thinking_budget" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.368885260225355, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 44.00407319020351, "unilateral_faults": 0, "wins": 67 }, { "admitted_plugins": 2, "attempted_matches": 144, "capped_draws": 52, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 72, "draws": 52, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 50, "max_score": null, "measured_at": "2026-07-27T10:59:27Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 144, "rating_method": "sequential_elo", "raw_elo": 1488.5751193579963, "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-mini", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.97743293260359, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 15.036461425079892, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 33, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T10:37:56Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1488.7884995268803, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.36207341877303, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 13 }, { "admitted_plugins": 4, "attempted_matches": 262, "capped_draws": 172, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 131, "draws": 172, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 46, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 262, "rating_method": "sequential_elo", "raw_elo": 1473.5547148296998, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.3268240179212, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.648363361490077, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugins": 1, "attempted_matches": 78, "capped_draws": 42, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 39, "draws": 42, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T10:59:32Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 78, "rating_method": "sequential_elo", "raw_elo": 1466.4677843586585, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.86645017234374, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 10 }, { "admitted_plugins": 3, "attempted_matches": 198, "capped_draws": 88, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 99, "draws": 88, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 67, "max_score": null, "measured_at": "2026-07-27T11:06:04Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 198, "rating_method": "sequential_elo", "raw_elo": 1467.3701302724855, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.39612230112461, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.42733990918024, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 49, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 49, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T09:14:03Z", "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": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1466.5807611762505, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.048681859229955, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 66, "capped_draws": 38, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T11:52:44Z", "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": 37, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1462.0021926743475, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.576018901450553, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 10 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 45, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T10:03:23Z", "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": 38, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1464.2474413129037, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.42690593498895, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3 }, { "admitted_plugins": 2, "attempted_matches": 88, "capped_draws": 50, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 44, "draws": 81, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:36:31Z", "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": 39, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 88, "rating_method": "sequential_elo", "raw_elo": 1472.7476833365188, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "balanced", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.422387009917625, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 32.006220619850886, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugins": 1, "attempted_matches": 72, "capped_draws": 25, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 36, "draws": 25, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:44:43Z", "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": 40, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 72, "rating_method": "sequential_elo", "raw_elo": 1457.7343014406704, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.232635390830257, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 23 }, { "admitted_plugins": 1, "attempted_matches": 74, "capped_draws": 47, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 37, "draws": 47, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T11:59:32Z", "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": 41, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1456.5863157614344, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.15214880984472, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 5 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 20, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 37, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:30:20Z", "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": 42, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1481.8014648809944, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.066723518033452, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.19324853318743, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 21, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 21, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T10:35:34Z", "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": 43, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1456.5400400197243, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.72984163252576, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 19 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 49, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 49, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T08:31:12Z", "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": 44, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1454.9766570016957, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.70399047704974, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 10 }, { "admitted_plugins": 1, "attempted_matches": 80, "capped_draws": 65, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 40, "draws": 65, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T10:42:50Z", "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": 45, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1450.2389966102576, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.438953458145875, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 66, "capped_draws": 53, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 53, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 46, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1449.6896851314627, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.668609009228703, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 49, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 49, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:36:28Z", "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": 47, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1451.714886192373, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.618761053818325, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 49, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 49, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T10:09:50Z", "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": 48, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1450.883258777918, "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": "other", "provider_model": "cohere/north-mini-code", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.6168805991318, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 68, "capped_draws": 57, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 57, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 49, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1446.802549177008, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.33186721946456, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3, "attempted_matches": 132, "capped_draws": 108, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 66, "draws": 108, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T10:53:40Z", "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": 50, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 132, "rating_method": "sequential_elo", "raw_elo": 1457.0274966044346, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.138347031709905, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 45, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:40:50Z", "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": 51, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1448.3295730196996, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.82065391961682, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 54, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 54, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T10:53:26Z", "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": 52, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1442.2170907590032, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.727323840541924, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3, "attempted_matches": 174, "capped_draws": 111, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 87, "draws": 111, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 41, "max_score": null, "measured_at": "2026-07-27T10:38:09Z", "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": 53, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 174, "rating_method": "sequential_elo", "raw_elo": 1445.4053682602037, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.50563948445921, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 21.363171103370707, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 38, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T10:53:39Z", "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": 54, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1452.3898563879034, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.41990029819383, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 45, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:30:17Z", "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": 55, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1443.826362619811, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_literal_legacy", "request_mode": "effort", "requested_effort": "medium", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.396699029090957, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 6 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 49, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 49, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:44:47Z", "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": 56, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1439.8208523917242, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.25028757645839, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 38, "capped_draws": 29, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 54, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:52:47Z", "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": 57, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1459.010175716237, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.1568688384384, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 41.18336395796551, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 3, "attempted_matches": 184, "capped_draws": 131, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 92, "draws": 131, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 58, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 184, "rating_method": "sequential_elo", "raw_elo": 1441.7341102563012, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.13021040956949, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 19.803385417785595, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 29, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 56, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T11:36:31Z", "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": 59, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1462.1361809829436, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.02024765518864, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.19324853318743, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 50, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:59:32Z", "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": 60, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1441.8619859707171, "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_literal_legacy", "request_mode": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.959030783411738, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1, "attempted_matches": 46, "capped_draws": 9, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 23, "draws": 21, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-27T11:04:07Z", "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": 61, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1453.7327498486231, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.952493120378215, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 36.2356618633981, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 48, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 48, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 62, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1440.8610223975368, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.6636526111786, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1 }, { "admitted_plugins": 3, "attempted_matches": 196, "capped_draws": 155, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 98, "draws": 155, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 63, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 196, "rating_method": "sequential_elo", "raw_elo": 1436.75553312595, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.61960427875735, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 17.700176346389366, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 24, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:30:10Z", "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": 64, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1458.736541116889, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.493587534338452, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 46.19324853318743, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 42, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 42, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T10:53:41Z", "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": 65, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1446.1686024506469, "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": "omitted", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "anthropic", "provider_setting_label": "Thinking disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Thinking disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.45612575749886, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 72, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-26T01:24:44Z", "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": 66, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1448.22814141271, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Enabled", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.335060663959837, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 43, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 43, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T10:52:42Z", "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": 67, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1439.4942097257222, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.304012940866215, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1 }, { "admitted_plugins": 2, "attempted_matches": 88, "capped_draws": 79, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 44, "draws": 79, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:53:34Z", "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": 68, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 88, "rating_method": "sequential_elo", "raw_elo": 1444.349744639428, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.174354772215807, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 48, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 48, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T10:53:26Z", "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": 69, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1432.8957272786026, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.06694876849134, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 47, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 47, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T10:42:48Z", "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": 70, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1438.2888976809872, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.961097857676517, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 42, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 42, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:30:14Z", "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": 71, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1436.2781128307956, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.953684555336736, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 27, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 58, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T10:51:37Z", "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": 72, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1450.4049907718822, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.71921399965224, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 42.0271267253503, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 2, "attempted_matches": 70, "capped_draws": 55, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 55, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T09:04:41Z", "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": 73, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1429.1142665897733, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.697480906486177, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 44, "capped_draws": 32, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 22, "draws": 58, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:03:50Z", "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": 74, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1447.3687877312982, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.696007242727312, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 38.41912513169022, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 37, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 37, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-26T21:50:12Z", "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": 75, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1438.8587143860132, "reasoning_level": "Highest", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": null, "requested_effort": "highest", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Highest", "reasoning_bracket": "intensive", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.32370388835863, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 65, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-26T02:17:44Z", "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": 76, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1441.610914575508, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.309943409461283, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 2 }, { "admitted_plugins": 2, "attempted_matches": 136, "capped_draws": 111, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 68, "draws": 111, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T10:53:39Z", "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": 77, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 136, "rating_method": "sequential_elo", "raw_elo": 1427.1095998713513, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.27875377434565, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 16.461902543922633, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 28, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 22, "draws": 54, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T10:53:39Z", "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": 78, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1445.100399542236, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.155907260050387, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 39.941634169259466, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 84, "capped_draws": 56, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 42, "draws": 109, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T10:59:44Z", "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": 79, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 84, "rating_method": "sequential_elo", "raw_elo": 1443.6062775081773, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.99822893746736, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 39.34626684974488, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 42, "capped_draws": 27, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 21, "draws": 42, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:06:04Z", "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": 80, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1445.205504297169, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.622792993226422, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 44.37464258315117, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 30, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 18, "draws": 30, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T10:42:48Z", "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": 81, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1440.4422887134535, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.61921497496216, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 29, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 69, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T10:53:27Z", "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": 82, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1435.9046812811634, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.52349474191262, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 33.54983807626827, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 2, "attempted_matches": 138, "capped_draws": 111, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 69, "draws": 111, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T10:59:43Z", "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": 83, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 138, "rating_method": "sequential_elo", "raw_elo": 1420.8052557973035, "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": true, "evidence_status": "retained_exact", "request_mode": "toggle", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.35282742604081, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 16.05264788810895, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 57, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-26T02:18:08Z", "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": 84, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1434.5293603256966, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Minimal", "reasoning_bracket": "baseline", "reasoning_bucket": "minimal", "reasoning_bucket_label": "Minimal", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "minimal" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.212894203087245, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 2, "attempted_matches": 140, "capped_draws": 113, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 70, "draws": 113, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T10:51:51Z", "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": 85, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 140, "rating_method": "sequential_elo", "raw_elo": 1416.3710347575352, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 23.723344738770017, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 2, "attempted_matches": 88, "capped_draws": 58, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 44, "draws": 103, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T11:05:59Z", "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": 86, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 88, "rating_method": "sequential_elo", "raw_elo": 1428.1658766468497, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Max", "reasoning_bracket": "intensive", "reasoning_bucket": "max", "reasoning_bucket_label": "Max", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "max" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.759434959312564, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 38.11029391633042, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 2, "attempted_matches": 66, "capped_draws": 38, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 33, "draws": 66, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 40, "max_score": null, "measured_at": "2026-07-27T11:52:44Z", "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": 87, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1432.644289501747, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.529651992284748, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 45.56239790693811, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 27, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 27, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T10:59:38Z", "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": 88, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1418.016037894468, "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": "effort", "requested_effort": "none", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "None", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "None", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.47989431367969, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 2, "attempted_matches": 138, "capped_draws": 89, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 69, "draws": 89, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 36, "max_score": null, "measured_at": "2026-07-27T10:59:44Z", "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": 89, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 138, "rating_method": "sequential_elo", "raw_elo": 1406.71166848003, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.174040290361702, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 16.016004726288628, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 2, "attempted_matches": 120, "capped_draws": 97, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 60, "draws": 97, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T10:42:49Z", "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": 90, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 120, "rating_method": "sequential_elo", "raw_elo": 1409.1936649870358, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning disabled", "reasoning_bracket": "baseline", "reasoning_bucket": "none", "reasoning_bucket_label": "Reasoning disabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.028323800205285, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 2 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 32, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-26T02:14:59Z", "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": 91, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1419.7799946445818, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Max", "reasoning_bracket": "intensive", "reasoning_bucket": "max", "reasoning_bucket_label": "Max", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "max" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.92797491218185, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 63, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 16, "max_score": null, "measured_at": "2026-07-26T01:24:45Z", "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": 92, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1418.4072460856055, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Minimal", "reasoning_bracket": "baseline", "reasoning_bucket": "minimal", "reasoning_bucket_label": "Minimal", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "minimal" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.7153135861437, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1, "attempted_matches": 62, "capped_draws": 57, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 57, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T11:44:31Z", "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": 93, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1402.0511352404135, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Medium", "reasoning_bracket": "balanced", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.05198164014908, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32, "capped_draws": 24, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 51, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T11:52:47Z", "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": 94, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1413.5850826874466, "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": "other", "provider_model": "cohere/north-mini-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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 19.858838132294075, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 28, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 18, "draws": 28, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:42:43Z", "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": 95, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1405.73919833146, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 19.24313559757037, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 25, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 54, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T10:59:21Z", "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": 96, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1400.630372981852, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "High", "reasoning_bracket": "intensive", "reasoning_bucket": "high", "reasoning_bucket_label": "High", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 18.44050863736999, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 38.53975118769762, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 15, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T10:42:50Z", "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": 97, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1479.2279924952009, "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/mixed" }, "provider_route": "openai", "provider_setting_label": "Low", "reasoning_bracket": "baseline", "reasoning_bucket": "low", "reasoning_bucket_label": "Low", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 17.83316943117343, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 69.22474682633933, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 12, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 12, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T10:53:25Z", "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": 98, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1370.0658232755432, "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_literal_legacy", "request_mode": "effort", "requested_effort": "xhigh", "source": "retained_generation_evidence", "track_id": "full_freedom/mixed" }, "provider_route": "openai", "provider_setting_label": "XHigh", "reasoning_bracket": "intensive", "reasoning_bucket": "xhigh", "reasoning_bucket_label": "XHigh", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 16.21797777560009, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 20 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 8, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 12, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T10:46:52Z", "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": 99, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1313.972577700416, "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/mixed" }, "provider_route": "openrouter", "provider_setting_label": "Reasoning enabled", "reasoning_bracket": "balanced", "reasoning_bucket": "enabled", "reasoning_bucket_label": "Reasoning enabled", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 3.452798895447958, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 51.15132550669373, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 40, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 40, "cell_count": 24, "cost_basis_counts": { "local_list_price_estimate": 48 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 8, "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": 33.78345 }, "codegen_evaluated_cells": 48, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 40, "failed_game_aliases": [ "GB2-06", "GB2-07", "GB2-08" ], "first_pass_admitted": 40, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:10:13Z", "losses": null, "max_score": 99.01057790596052, "measured_at": null, "min_score": 43.019463779962486, "model_code_failure_rate": 0.16666666666666666, "model_code_failures": 8, "model_display_name": "Claude Opus 5", "model_slug": "claude-opus-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1700.259156381626, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 67.23813069766389, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 24, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 24, "cell_count": 24, "cost_basis_counts": { "local_standard_estimate": 28 }, "evidence_basis": "Standard list-price estimate", "max": 3.2933475, "mean": 1.078263125, "median": 0.5065824999999999, "min": 0.06826499999999999, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 28 }, "run_count": 24, "token_priced_attempt_count": 28, "total": 25.878315 }, "codegen_evaluated_cells": 24, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 24, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:53:35Z", "losses": null, "max_score": 100.0, "measured_at": null, "min_score": 25.753419845975525, "model_code_failure_rate": 0.0, "model_code_failures": 0, "model_display_name": "GPT-5.4", "model_slug": "gpt-5-4", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1608.526152886236, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 4, "repaired_rate": 0.16666666666666666, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 57.62022282317851, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 24, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 24, "cell_count": 24, "cost_basis_counts": { "local_standard_estimate": 27 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 2, "max": 12.915325, "mean": 3.549568958333333, "median": 0.4352825, "min": 0.09045, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 27 }, "run_count": 26, "token_priced_attempt_count": 27, "total": 85.66335499999998 }, "codegen_evaluated_cells": 26, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 24, "failed_game_aliases": [ "GB2-04", "GB2-06" ], "first_pass_admitted": 23, "first_pass_rate": 0.8846153846153846, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "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": "2026-07-27T11:59:44Z", "losses": null, "max_score": 100.0, "measured_at": null, "min_score": 16.21797777560009, "model_code_failure_rate": 0.07692307692307693, "model_code_failures": 2, "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": 0, "rating_method": "sequential_elo", "raw_elo": 1583.4666766152122, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 1, "repaired_rate": 0.038461538461538464, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 56.05515981160776, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 59, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 59, "cell_count": 24, "cost_basis_counts": { "provider_reported": 104 }, "evidence_basis": "Provider-reported", "failed_cell_count": 5, "max": 0.14454373333333334, "mean": 0.08597182777777779, "median": 0.08538879999999999, "min": 0.041110400000000005, "recorded_attempt_count": 104, "run_count": 64, "total": 5.56697 }, "codegen_evaluated_cells": 64, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 91, "failed_game_aliases": [ "GB2-02", "GB2-03", "GB2-05" ], "first_pass_admitted": 27, "first_pass_rate": 0.421875, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "GB2-05", "GB2-06", "GB2-07", "GB2-08" ], "infra_failures_excluded": 16, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:53:35Z", "losses": null, "max_score": 84.85770377828395, "measured_at": null, "min_score": 19.6056169247618, "model_code_failure_rate": 0.078125, "model_code_failures": 5, "model_display_name": "Grok 4.5", "model_slug": "x-ai-grok-4-5", "plugin_success_rate": null, "provider": "xAI", "provider_key": "x-ai", "rank": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1577.6722068347774, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 32, "repaired_rate": 0.5, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 51.49090649703385, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 22, "attempted_matches": 0, "capped_draws": 0, "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-2026-07-25": 26 }, "run_count": 24, "token_priced_attempt_count": 26, "total": 26.566350000000007 }, "codegen_evaluated_cells": 24, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 22, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:58Z", "losses": null, "max_score": 88.73890042665397, "measured_at": null, "min_score": 27.47820671040979, "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1576.563381059858, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 1, "repaired_rate": 0.041666666666666664, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 51.398075670184305, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 24, "attempted_matches": 0, "capped_draws": 0, "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": 12.13752, "mean": 2.8005991666666663, "median": 0.158095, "min": 0.0542775, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 32 }, "run_count": 25, "token_priced_attempt_count": 32, "total": 67.27386999999999 }, "codegen_evaluated_cells": 25, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 24, "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 }, "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": "2026-07-27T11:59:44Z", "losses": null, "max_score": 72.98349769903467, "measured_at": null, "min_score": 28.668609009228703, "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1521.9174955981157, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 7, "repaired_rate": 0.28, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 46.31809271032358, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 22, "attempted_matches": 0, "capped_draws": 0, "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": 0.203055, "min": 0.131495, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 25 }, "run_count": 24, "token_priced_attempt_count": 25, "total": 10.456239999999998 }, "codegen_evaluated_cells": 24, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 22, "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 }, "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": "2026-07-27T11:54:26Z", "losses": null, "max_score": 76.32595670280091, "measured_at": null, "min_score": 26.60687800872694, "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1566.3703314296458, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 1, "repaired_rate": 0.041666666666666664, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 45.99009483614247, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 49, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 49, "cell_count": 24, "cost_basis_counts": { "provider_reported": 97 }, "evidence_basis": "Provider-reported", "failed_cell_count": 6, "max": 0.9392418, "mean": 0.3752466458333333, "median": 0.32150055, "min": 0.0587988, "recorded_attempt_count": 97, "run_count": 55, "total": 22.9788486 }, "codegen_evaluated_cells": 55, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 88, "failed_game_aliases": [ "GB2-03", "GB2-05", "GB2-06" ], "first_pass_admitted": 16, "first_pass_rate": 0.2909090909090909, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [ "GB2-02", "GB2-08" ], "infra_failures_excluded": 3, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": null, "max_score": 67.21194886050958, "measured_at": null, "min_score": 20.580987520067197, "model_code_failure_rate": 0.10909090909090909, "model_code_failures": 6, "model_display_name": "Kimi K3", "model_slug": "moonshotai-kimi-k3", "plugin_success_rate": null, "provider": "Moonshot", "provider_key": "moonshotai", "rank": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1539.9576408004175, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 33, "repaired_rate": 0.6, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 45.987768375465144, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 24, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 24, "cell_count": 24, "cost_basis_counts": { "local_standard_estimate": 28 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 2, "max": 4.987857, "mean": 1.074231, "median": 0.038529, "min": 0.016152, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 28 }, "run_count": 26, "token_priced_attempt_count": 28, "total": 29.297331 }, "codegen_evaluated_cells": 26, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 24, "failed_game_aliases": [ "GB2-03", "GB2-06" ], "first_pass_admitted": 22, "first_pass_rate": 0.8461538461538461, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "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": "2026-07-27T11:59:32Z", "losses": null, "max_score": 75.31262484978316, "measured_at": null, "min_score": 0.0, "model_code_failure_rate": 0.07692307692307693, "model_code_failures": 2, "model_display_name": "GPT-5.6 Luna", "model_slug": "gpt-5-6-luna", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1480.7743300347563, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 2, "repaired_rate": 0.07692307692307693, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 40.289803298523225, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 59, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 59, "cell_count": 23, "cost_basis_counts": { "local_standard_estimate": 70 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 1, "max": 1.5164726249999998, "mean": 0.3999331141304348, "median": 0.2331955, "min": 0.01259225, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 70 }, "run_count": 60, "token_priced_attempt_count": 70, "total": 18.42633 }, "codegen_evaluated_cells": 60, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 59, "failed_game_aliases": [ "GB2-06" ], "first_pass_admitted": 51, "first_pass_rate": 0.85, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [ "GB2-01", "GB2-03", "GB2-04" ], "infra_failures_excluded": 6, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": null, "max_score": 66.30476749736133, "measured_at": null, "min_score": 21.382657975617843, "model_code_failure_rate": 0.016666666666666666, "model_code_failures": 1, "model_display_name": "GPT-5.4 Mini", "model_slug": "gpt-5-4-mini", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1473.9398128976704, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 8, "repaired_rate": 0.13333333333333333, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 39.78288745492075, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 47, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 47, "cell_count": 24, "cost_basis_counts": { "provider_reported": 89 }, "evidence_basis": "Provider-reported", "failed_cell_count": 1, "max": 0.04815395, "mean": 0.025957827083333333, "median": 0.02516155, "min": 0.00845595, "recorded_attempt_count": 89, "run_count": 48, "total": 1.2459757000000002 }, "codegen_evaluated_cells": 48, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 46, "failed_game_aliases": [ "GB2-03" ], "first_pass_admitted": 10, "first_pass_rate": 0.20833333333333337, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:23:13Z", "losses": null, "max_score": 66.08096329718745, "measured_at": null, "min_score": 13.059186845663168, "model_code_failure_rate": 0.020833333333333332, "model_code_failures": 1, "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1466.7704487027802, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 37, "repaired_rate": 0.7708333333333334, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 36.95526751593128, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 65, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 65, "cell_count": 24, "cost_basis_counts": { "local_standard_estimate": 130 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 16, "max": 0.38568888333333334, "mean": 0.10861519774305556, "median": 0.02520601875, "min": 0.0058062875, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 130 }, "run_count": 81, "token_priced_attempt_count": 130, "total": 6.1442373 }, "codegen_evaluated_cells": 81, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 65, "failed_game_aliases": [ "GB2-02", "GB2-03", "GB2-04", "GB2-05", "GB2-06", "GB2-07", "GB2-08" ], "first_pass_admitted": 33, "first_pass_rate": 0.4074074074074074, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [ "GB2-01", "GB2-03", "GB2-04", "GB2-05", "GB2-06", "GB2-07" ], "infra_failures_excluded": 9, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": null, "max_score": 54.484864054652334, "measured_at": null, "min_score": 19.139574631625756, "model_code_failure_rate": 0.19753086419753085, "model_code_failures": 16, "model_display_name": "GPT-5.4 Nano", "model_slug": "gpt-5-4-nano", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1462.6122873444106, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 32, "repaired_rate": 0.3950617283950617, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 34.34057217679145, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 20, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 20, "cell_count": 24, "cost_basis_counts": { "provider_reported": 47 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.01660212, "mean": 0.004222185916666667, "median": 0.0025298300000000003, "min": 0.00045831, "recorded_attempt_count": 47, "run_count": 24, "total": 0.10133246200000004 }, "codegen_evaluated_cells": 24, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 25, "failed_game_aliases": [ "GB2-01", "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:32Z", "losses": null, "max_score": 60.76783956869306, "measured_at": null, "min_score": 14.420068188974202, "model_code_failure_rate": 0.16666666666666666, "model_code_failures": 4, "model_display_name": "GPT-OSS 120B", "model_slug": "openai-gpt-oss-120b", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1465.2074625457594, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 14, "repaired_rate": 0.5833333333333334, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 31.27854371239756, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 15, "attempted_matches": 0, "capped_draws": 0, "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-2026-07-25": 19 }, "run_count": 16, "token_priced_attempt_count": 19, "total": 16.698169999999998 }, "codegen_evaluated_cells": 16, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 15, "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 }, "infra_excluded_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04" ], "infra_failures_excluded": 4, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:46:35Z", "losses": null, "max_score": 100.0, "measured_at": null, "min_score": 49.32044382130511, "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": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 3, "repaired_rate": 0.1875, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 73.1109201148505, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 40, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 40, "cell_count": 24, "cost_basis_counts": { "provider_reported": 82 }, "evidence_basis": "Provider-reported", "failed_cell_count": 8, "max": 0.341716425, "mean": 0.17334414687500002, "median": 0.166217925, "min": 0.029012250000000003, "recorded_attempt_count": 82, "run_count": 48, "total": 8.320519050000001 }, "codegen_evaluated_cells": 48, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 40, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "GB2-05", "GB2-07" ], "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:26:38Z", "losses": null, "max_score": 89.93824120320421, "measured_at": null, "min_score": 22.174040290361702, "model_code_failure_rate": 0.16666666666666666, "model_code_failures": 8, "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": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1548.5197652395502, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 24, "repaired_rate": 0.5, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 46.884401886076766, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 8, "attempted_matches": 0, "capped_draws": 0, "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": 0.73533, "mean": 0.29615479166666664, "median": 0.1968175, "min": 0.09594, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 16, "boardgame-list-prices-2026-07-25": 8 }, "run_count": 24, "token_priced_attempt_count": 24, "total": 7.107715000000001 }, "codegen_evaluated_cells": 8, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": null, "max_score": 57.75514722037097, "measured_at": null, "min_score": 35.54624651592337, "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": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 46.10653397009744, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 14, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 14, "cell_count": 16, "cost_basis_counts": { "provider_reported": 37 }, "evidence_basis": "Provider-reported", "failed_cell_count": 2, "max": 0.6921525, "mean": 0.41891503125, "median": 0.4031475, "min": 0.254883, "recorded_attempt_count": 37, "run_count": 16, "total": 6.702640499999999 }, "codegen_evaluated_cells": 16, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 20, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:53:34Z", "losses": null, "max_score": 89.02948337376621, "measured_at": null, "min_score": 18.44050863736999, "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": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 14, "repaired_rate": 0.875, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 45.22530327465701, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 14, "attempted_matches": 0, "capped_draws": 0, "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": 0.121855, "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": 0, "draws": null, "entry_count": 21, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:32Z", "losses": null, "max_score": 78.20945134532496, "measured_at": null, "min_score": 28.574021625817625, "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": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 6, "repaired_rate": 0.375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 42.007132433322745, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 15, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 15, "cell_count": 16, "cost_basis_counts": { "local_standard_estimate": 19 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 1, "max": 0.454645, "mean": 0.22978835937499997, "median": 0.1997375, "min": 0.1418975, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 19 }, "run_count": 16, "token_priced_attempt_count": 19, "total": 3.67661375 }, "codegen_evaluated_cells": 16, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 23, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:53:48Z", "losses": null, "max_score": 62.019294143192774, "measured_at": null, "min_score": 24.622792993226422, "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": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 3, "repaired_rate": 0.1875, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 41.678929340000025, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 17, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 17, "cell_count": 16, "cost_basis_counts": { "local_list_price_estimate": 19 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 1, "max": 0.4567, "mean": 0.2220434166666667, "median": 0.183367, "min": 0.05673, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 2, "boardgame-list-prices-2026-07-25": 17 }, "run_count": 18, "token_priced_attempt_count": 19, "total": 4.168736000000001 }, "codegen_evaluated_cells": 18, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 25, "failed_game_aliases": [ "GB2-03" ], "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 }, "infra_excluded_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "GB2-05", "GB2-06", "GB2-07", "GB2-08" ], "infra_failures_excluded": 18, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:58Z", "losses": null, "max_score": 58.84535558133786, "measured_at": null, "min_score": 26.09668923633087, "model_code_failure_rate": 0.05555555555555555, "model_code_failures": 1, "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": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1498.2303510224829, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 1, "repaired_rate": 0.05555555555555555, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 41.49387209065529, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 18, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 18, "cell_count": 24, "cost_basis_counts": { "local_standard_estimate": 29 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 6, "max": 0.136952, "mean": 0.056666249999999994, "median": 0.050531999999999994, "min": 0.03731, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 13, "boardgame-list-prices-2026-07-25": 16 }, "run_count": 24, "token_priced_attempt_count": 29, "total": 1.3599900000000005 }, "codegen_evaluated_cells": 24, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 26, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04" ], "first_pass_admitted": 14, "first_pass_rate": 0.5833333333333334, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "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": "2026-07-27T11:59:44Z", "losses": null, "max_score": 83.5076304126712, "measured_at": null, "min_score": 17.83316943117343, "model_code_failure_rate": 0.25, "model_code_failures": 6, "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": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1522.9925903227006, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 4, "repaired_rate": 0.16666666666666666, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 40.65113726350103, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 19, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 19, "cell_count": 8, "cost_basis_counts": { "provider_reported": 57 }, "evidence_basis": "Provider-reported", "failed_cell_count": 8, "max": 0.25293804044999996, "mean": 0.19953128278325, "median": 0.20662718916666667, "min": 0.13279406625, "recorded_attempt_count": 57, "run_count": 27, "total": 5.24138213703 }, "codegen_evaluated_cells": 27, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 63, "failed_game_aliases": [ "GB2-01", "GB2-03", "GB2-04", "GB2-06" ], "first_pass_admitted": 1, "first_pass_rate": 0.037037037037037035, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [ "GB2-03", "GB2-06" ], "infra_failures_excluded": 2, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:37:08Z", "losses": null, "max_score": 68.70041680687149, "measured_at": null, "min_score": 24.41934796442663, "model_code_failure_rate": 0.2962962962962963, "model_code_failures": 8, "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": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1509.8332480473232, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 18, "repaired_rate": 0.6666666666666666, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 40.584909218159005, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 13, "attempted_matches": 0, "capped_draws": 0, "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": 0, "draws": null, "entry_count": 13, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": null, "max_score": 76.49983872640665, "measured_at": null, "min_score": 21.132140682151817, "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": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 8, "repaired_rate": 0.5, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 40.49604885328687, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 12, "attempted_matches": 0, "capped_draws": 0, "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": 0, "draws": null, "entry_count": 17, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:51Z", "losses": null, "max_score": 65.31899895038302, "measured_at": null, "min_score": 25.71921399965224, "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": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 8, "repaired_rate": 0.5333333333333333, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 39.60492019451364, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 23, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 23, "cell_count": 16, "cost_basis_counts": { "provider_reported": 45 }, "evidence_basis": "Provider-reported", "failed_cell_count": 5, "max": 0.00596013, "mean": 0.0023166812500000004, "median": 0.00193686, "min": 0.00093502, "recorded_attempt_count": 45, "run_count": 28, "total": 0.06608082 }, "codegen_evaluated_cells": 28, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 23, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-04", "GB2-07" ], "first_pass_admitted": 13, "first_pass_rate": 0.4642857142857143, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [ "GB2-04", "GB2-06" ], "infra_failures_excluded": 4, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:54:26Z", "losses": null, "max_score": 58.36812405939523, "measured_at": null, "min_score": 23.723344738770017, "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": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 10, "repaired_rate": 0.35714285714285715, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 37.78788584262696, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 0, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 8, "failed_game_aliases": [], "first_pass_admitted": null, "first_pass_rate": null, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:48:31Z", "losses": null, "max_score": 56.67090350467359, "measured_at": null, "min_score": 22.47989431367969, "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": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 37.36024586658148, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 8, "attempted_matches": 0, "capped_draws": 0, "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": 0.4852845999999999 }, "codegen_evaluated_cells": 8, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 16, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:30:10Z", "losses": null, "max_score": 53.83120272886001, "measured_at": null, "min_score": 26.493587534338452, "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": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 8, "repaired_rate": 1.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 36.60929744604539, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 26, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 26, "cell_count": 16, "cost_basis_counts": { "provider_reported": 57 }, "evidence_basis": "Provider-reported", "failed_cell_count": 6, "max": 0.04649778, "mean": 0.024494787749999997, "median": 0.022485588, "min": 0.004429524000000001, "recorded_attempt_count": 57, "run_count": 32, "total": 0.7838332079999999 }, "codegen_evaluated_cells": 32, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 26, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "GB2-07" ], "first_pass_admitted": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:54:00Z", "losses": null, "max_score": 52.38713921457689, "measured_at": null, "min_score": 19.697931844478177, "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": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 18, "repaired_rate": 0.5625, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 36.07115177214229, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 6, "attempted_matches": 0, "capped_draws": 0, "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": 0, "draws": null, "entry_count": 12, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:03:48Z", "losses": null, "max_score": 47.67871891237462, "measured_at": null, "min_score": 24.01242101325399, "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": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 35.33269037618208, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 32, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 32, "cell_count": 16, "cost_basis_counts": { "provider_reported": 81 }, "evidence_basis": "Provider-reported", "failed_cell_count": 13, "max": 0.02904086, "mean": 0.01148428059375, "median": 0.006669530066666667, "min": 0.0016912200000000002, "recorded_attempt_count": 81, "run_count": 45, "total": 0.4929778278 }, "codegen_evaluated_cells": 45, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 52, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "GB2-06", "GB2-07", "GB2-08" ], "first_pass_admitted": 13, "first_pass_rate": 0.28888888888888886, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [ "GB2-03", "GB2-06", "GB2-07" ], "infra_failures_excluded": 3, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:54:00Z", "losses": null, "max_score": 51.110878446006915, "measured_at": null, "min_score": 21.605010778009973, "model_code_failure_rate": 0.28888888888888886, "model_code_failures": 13, "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": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1453.5431927615102, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 19, "repaired_rate": 0.4222222222222222, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 33.58432834211232, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 28, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 28, "cell_count": 24, "cost_basis_counts": { "provider_reported": 102 }, "evidence_basis": "Provider-reported", "failed_cell_count": 20, "max": 0.213668025, "mean": 0.08694262229166666, "median": 0.059337825, "min": 0.012912625, "recorded_attempt_count": 102, "run_count": 48, "total": 4.17324587 }, "codegen_evaluated_cells": 48, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 28, "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": 0.14583333333333334, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:37:44Z", "losses": null, "max_score": 55.633695043376434, "measured_at": null, "min_score": 21.92797491218185, "model_code_failure_rate": 0.4166666666666667, "model_code_failures": 20, "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": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1460.6834451696127, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 21, "repaired_rate": 0.4375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 33.31537421869243, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 30, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 30, "cell_count": 16, "cost_basis_counts": { "provider_reported": 60 }, "evidence_basis": "Provider-reported", "failed_cell_count": 9, "max": 0.015971877, "mean": 0.006007524767083333, "median": 0.0031725295999999997, "min": 0.001825724, "recorded_attempt_count": 60, "run_count": 39, "total": 0.19590749698 }, "codegen_evaluated_cells": 39, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 44, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "GB2-06" ], "first_pass_admitted": 19, "first_pass_rate": 0.4871794871794872, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [ "GB2-08" ], "infra_failures_excluded": 1, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": null, "max_score": 51.48147323629893, "measured_at": null, "min_score": 24.11930639666456, "model_code_failure_rate": 0.2307692307692308, "model_code_failures": 9, "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": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1431.3049058972535, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 11, "repaired_rate": 0.28205128205128205, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 33.12354951023329, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 13, "attempted_matches": 0, "capped_draws": 0, "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": 0.78755832 }, "codegen_evaluated_cells": 16, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 20, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:47Z", "losses": null, "max_score": 52.69666989897096, "measured_at": null, "min_score": 12.243419652002428, "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": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 9, "repaired_rate": 0.5625, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 32.916331924462284, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 12, "attempted_matches": 0, "capped_draws": 0, "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": 0, "draws": null, "entry_count": 18, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:44:24Z", "losses": null, "max_score": 58.39911627396981, "measured_at": null, "min_score": 18.05367245403799, "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": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 7, "repaired_rate": 0.4117647058823529, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 32.81840659142981, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 16, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 16, "cell_count": 24, "cost_basis_counts": { "provider_reported": 55 }, "evidence_basis": "Provider-reported", "failed_cell_count": 8, "max": 0.08193244999999999, "mean": 0.03901218041666666, "median": 0.03030545, "min": 0.00984735, "recorded_attempt_count": 55, "run_count": 24, "total": 0.9362923300000002 }, "codegen_evaluated_cells": 24, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 21, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "GB2-07", "GB2-08" ], "first_pass_admitted": 1, "first_pass_rate": 0.041666666666666664, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:46:13Z", "losses": null, "max_score": 53.536938067285334, "measured_at": null, "min_score": 19.24313559757037, "model_code_failure_rate": 0.3333333333333333, "model_code_failures": 8, "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": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1450.432771430463, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 15, "repaired_rate": 0.625, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 32.52748811060747, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 13, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 13, "cell_count": 16, "cost_basis_counts": { "provider_reported": 24 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.0056201515, "mean": 0.00210600034375, "median": 0.0014932259999999998, "min": 0.00090937, "recorded_attempt_count": 24, "run_count": 17, "total": 0.039316157 }, "codegen_evaluated_cells": 17, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 20, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:48:11Z", "losses": null, "max_score": 71.25680984831166, "measured_at": null, "min_score": 18.058264435137527, "model_code_failure_rate": 0.2352941176470588, "model_code_failures": 4, "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": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 4, "repaired_rate": 0.2352941176470588, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 31.86728280223101, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 10, "attempted_matches": 0, "capped_draws": 0, "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": 0.06253070000000001 }, "codegen_evaluated_cells": 14, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 14, "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 }, "infra_excluded_game_aliases": [ "GB2-01", "GB2-02" ], "infra_failures_excluded": 2, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:24:44Z", "losses": null, "max_score": 44.68186759149837, "measured_at": null, "min_score": 21.93738491295836, "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": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 5, "repaired_rate": 0.35714285714285715, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 31.220699476019774, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 12, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 12, "cell_count": 16, "cost_basis_counts": { "provider_reported": 50 }, "evidence_basis": "Provider-reported", "failed_cell_count": 12, "max": 0.2156775, "mean": 0.12996646093750003, "median": 0.12798825, "min": 0.061553, "recorded_attempt_count": 50, "run_count": 24, "total": 3.3391555 }, "codegen_evaluated_cells": 24, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 17, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": null, "max_score": 68.47656737578293, "measured_at": null, "min_score": 3.452798895447958, "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": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 12, "repaired_rate": 0.5, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 30.92202088844704, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 14, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 14, "cell_count": 16, "cost_basis_counts": { "provider_reported": 52 }, "evidence_basis": "Provider-reported", "failed_cell_count": 11, "max": 0.0445032, "mean": 0.030658954687500004, "median": 0.0312573, "min": 0.01864685, "recorded_attempt_count": 52, "run_count": 25, "total": 0.75384265 }, "codegen_evaluated_cells": 25, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 30, "failed_game_aliases": [ "GB2-01", "GB2-03", "GB2-04", "GB2-05", "GB2-06", "GB2-07" ], "first_pass_admitted": 2, "first_pass_rate": 0.08, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:38Z", "losses": null, "max_score": 59.81864880409941, "measured_at": null, "min_score": 5.146710224123554, "model_code_failure_rate": 0.44, "model_code_failures": 11, "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": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1462.9486169052536, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 12, "repaired_rate": 0.48, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 29.420353974702792, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 17, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 17, "cell_count": 16, "cost_basis_counts": { "provider_reported": 63 }, "evidence_basis": "Provider-reported", "failed_cell_count": 14, "max": 0.0, "mean": 0.0, "median": 0.0, "min": 0.0, "recorded_attempt_count": 63, "run_count": 31, "total": 0.0 }, "codegen_evaluated_cells": 31, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 17, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "GB2-05", "GB2-07", "GB2-08" ], "first_pass_admitted": 6, "first_pass_rate": 0.1935483870967742, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [ "GB2-05" ], "infra_failures_excluded": 1, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:37:35Z", "losses": null, "max_score": 44.131890322774105, "measured_at": null, "min_score": 18.594475422927697, "model_code_failure_rate": 0.4516129032258064, "model_code_failures": 14, "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": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "openrouter", "provider_setting_label": null, "reasoning_bracket": null, "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 11, "repaired_rate": 0.3548387096774194, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 27.827749194310456, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 11, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 11, "cell_count": 16, "cost_basis_counts": { "provider_reported": 44 }, "evidence_basis": "Provider-reported", "failed_cell_count": 13, "max": 0.0, "mean": 0.0, "median": 0.0, "min": 0.0, "recorded_attempt_count": 44, "run_count": 24, "total": 0.0 }, "codegen_evaluated_cells": 24, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 17, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:47Z", "losses": null, "max_score": 42.997436567986185, "measured_at": null, "min_score": 19.858838132294075, "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": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "openrouter", "provider_setting_label": null, "reasoning_bracket": null, "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 5, "repaired_rate": 0.20833333333333337, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 25.24402606113204, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 11, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 11, "cell_count": 16, "cost_basis_counts": { "provider_reported": 34 }, "evidence_basis": "Provider-reported", "failed_cell_count": 5, "max": 0.0422995, "mean": 0.017778359375, "median": 0.017199625, "min": 0.00402875, "recorded_attempt_count": 34, "run_count": 16, "total": 0.28445375 }, "codegen_evaluated_cells": 16, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 21, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03" ], "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:53:48Z", "losses": null, "max_score": 42.33396509337835, "measured_at": null, "min_score": 0.0, "model_code_failure_rate": 0.3125, "model_code_failures": 5, "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": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1316.1721101845894, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 9, "repaired_rate": 0.5625, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 24.86973235573043, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 8, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 16, "cost_basis_counts": { "provider_reported": 27 }, "evidence_basis": "Provider-reported", "failed_cell_count": 9, "max": 0.33185775, "mean": 0.112831453125, "median": 0.0747585, "min": 0.0223935, "recorded_attempt_count": 27, "run_count": 17, "total": 2.137161 }, "codegen_evaluated_cells": 17, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 12, "failed_game_aliases": [ "GB2-02", "GB2-03", "GB2-04", "GB2-07", "GB2-08" ], "first_pass_admitted": 4, "first_pass_rate": 0.2352941176470588, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:31Z", "losses": null, "max_score": 38.70088877553203, "measured_at": null, "min_score": 14.82966031579288, "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": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "partial", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": null }, "repaired_admitted": 4, "repaired_rate": 0.2352941176470588, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 22.165076869476923, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 14, "attempted_matches": 710, "capped_draws": 7, "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": 0.4461796875, "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": 71.8966107628626, "contributing_entrants": null, "distinct_rated_opponents": 355, "draws": 99, "entry_count": 14, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:10:13Z", "losses": 180, "max_score": 91.93118700577348, "measured_at": null, "min_score": 43.019463779962486, "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": 710, "rating_method": "sequential_elo", "raw_elo": 1702.303798928371, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 69.53611634620681, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 431 }, { "admitted_plugins": 7, "attempted_matches": 388, "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-2026-07-25": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 4.0371999999999995 }, "codegen_evaluated_cells": 8, "conditional_success_score": 65.00100860904149, "contributing_entrants": null, "distinct_rated_opponents": 194, "draws": 59, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:25:35Z", "losses": 108, "max_score": 76.52631679447857, "measured_at": null, "min_score": 49.32044382130511, "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 388, "rating_method": "sequential_elo", "raw_elo": 1646.7741909355173, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 62.86690915330064, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 221 }, { "admitted_plugins": 23, "attempted_matches": 1502, "capped_draws": 42, "codegen_cost_usd": { "admitted_cell_count": 23, "cell_count": 8, "cost_basis_counts": { "provider_reported": 39 }, "evidence_basis": "Provider-reported", "failed_cell_count": 1, "max": 0.12366493333333332, "mean": 0.09185773333333332, "median": 0.09170913333333332, "min": 0.04980146666666666, "recorded_attempt_count": 39, "run_count": 24, "total": 2.2045855999999997 }, "codegen_evaluated_cells": 24, "conditional_success_score": 60.64883527347195, "contributing_entrants": null, "distinct_rated_opponents": 750, "draws": 344, "entry_count": 23, "failed_game_aliases": [ "GB2-02" ], "first_pass_admitted": 10, "first_pass_rate": 0.4166666666666667, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "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": "2026-07-27T11:52:52Z", "losses": 416, "max_score": 84.85770377828395, "measured_at": null, "min_score": 37.60021583373031, "model_code_failure_rate": 0.041666666666666664, "model_code_failures": 1, "model_display_name": "Grok 4.5", "model_slug": "x-ai-grok-4-5", "plugin_success_rate": 0.9583333333333334, "provider": "xAI", "provider_key": "x-ai", "rank": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1502, "rating_method": "sequential_elo", "raw_elo": 1615.257839866562, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": 13, "repaired_rate": 0.5416666666666666, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 60.006958322299816, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 742 }, { "admitted_plugins": 8, "attempted_matches": 442, "capped_draws": 7, "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": 0.6689649999999999, "mean": 0.46799875, "median": 0.4352825, "min": 0.366615, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 10 }, "run_count": 9, "token_priced_attempt_count": 10, "total": 4.1199200000000005 }, "codegen_evaluated_cells": 9, "conditional_success_score": 59.573031480400935, "contributing_entrants": null, "distinct_rated_opponents": 221, "draws": 101, "entry_count": 8, "failed_game_aliases": [ "GB2-06" ], "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 }, "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": "2026-07-27T11:52:52Z", "losses": 122, "max_score": 74.1340312841928, "measured_at": null, "min_score": 34.15864897798004, "model_code_failure_rate": 0.1111111111111111, "model_code_failures": 1, "model_display_name": "GPT-5.6 Sol", "model_slug": "gpt-5-6-sol", "plugin_success_rate": 0.8888888888888888, "provider": "OpenAI", "provider_key": "openai", "rank": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 442, "rating_method": "sequential_elo", "raw_elo": 1602.640138463198, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.1111111111111111, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 57.844433198792, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 8, "attempted_matches": 454, "capped_draws": 57, "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": 52.00774565635941, "contributing_entrants": null, "distinct_rated_opponents": 226, "draws": 159, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:57Z", "losses": 112, "max_score": 89.02948337376621, "measured_at": null, "min_score": 21.05198164014908, "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 452, "rating_method": "sequential_elo", "raw_elo": 1565.2269025940584, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 8, "repaired_rate": 1.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 52.00774565635941, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 181 }, { "admitted_plugins": 16, "attempted_matches": 1025, "capped_draws": 127, "codegen_cost_usd": { "admitted_cell_count": 16, "cell_count": 8, "cost_basis_counts": { "provider_reported": 29 }, "evidence_basis": "Provider-reported", "max": 0.25698975, "mean": 0.172479834375, "median": 0.166217925, "min": 0.10864875, "recorded_attempt_count": 29, "run_count": 16, "total": 2.75967735 }, "codegen_evaluated_cells": 16, "conditional_success_score": 49.29082044256339, "contributing_entrants": null, "distinct_rated_opponents": 512, "draws": 379, "entry_count": 16, "failed_game_aliases": [], "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:37:40Z", "losses": 261, "max_score": 79.77925593934339, "measured_at": null, "min_score": 22.174040290361702, "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1024, "rating_method": "sequential_elo", "raw_elo": 1549.0656151440612, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": 12, "repaired_rate": 0.75, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 49.29082044256339, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 384 }, { "admitted_plugins": 8, "attempted_matches": 478, "capped_draws": 47, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 9 }, "evidence_basis": "Standard list-price estimate", "max": 0.712055, "mean": 0.49864374999999994, "median": 0.5065824999999999, "min": 0.29423750000000004, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 3.989149999999999 }, "codegen_evaluated_cells": 8, "conditional_success_score": 48.349371100347874, "contributing_entrants": null, "distinct_rated_opponents": 239, "draws": 179, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:56Z", "losses": 129, "max_score": 90.34672640532096, "measured_at": null, "min_score": 25.753419845975525, "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": 478, "rating_method": "sequential_elo", "raw_elo": 1545.839712781073, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 48.349371100347874, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 170 }, { "admitted_plugins": 8, "attempted_matches": 450, "capped_draws": 65, "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": 0.442856875, "median": 0.4176025, "min": 0.34269, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 3.5428550000000003 }, "codegen_evaluated_cells": 8, "conditional_success_score": 48.01639254386449, "contributing_entrants": null, "distinct_rated_opponents": 225, "draws": 152, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:58Z", "losses": 142, "max_score": 65.72170653066799, "measured_at": null, "min_score": 27.47820671040979, "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": 450, "rating_method": "sequential_elo", "raw_elo": 1539.8710077025632, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 48.01639254386449, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 156 }, { "admitted_plugins": 8, "attempted_matches": 458, "capped_draws": 72, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 9 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 1, "max": 0.046574, "mean": 0.036155625, "median": 0.035338, "min": 0.025803, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 9 }, "run_count": 9, "token_priced_attempt_count": 9, "total": 0.315048 }, "codegen_evaluated_cells": 9, "conditional_success_score": 48.244974243672814, "contributing_entrants": null, "distinct_rated_opponents": 229, "draws": 204, "entry_count": 8, "failed_game_aliases": [ "GB2-06" ], "first_pass_admitted": 8, "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 }, "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": "2026-07-27T11:44:52Z", "losses": 125, "max_score": 65.00304603642252, "measured_at": null, "min_score": 30.997988769059855, "model_code_failure_rate": 0.1111111111111111, "model_code_failures": 1, "model_display_name": "GPT-5.6 Luna", "model_slug": "gpt-5-6-luna", "plugin_success_rate": 0.8888888888888888, "provider": "OpenAI", "provider_key": "openai", "rank": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 458, "rating_method": "sequential_elo", "raw_elo": 1531.3726221137415, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 46.8450760430698, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 129 }, { "admitted_plugins": 8, "attempted_matches": 420, "capped_draws": 63, "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-2026-07-25": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 1.743525 }, "codegen_evaluated_cells": 8, "conditional_success_score": 45.15308829494262, "contributing_entrants": null, "distinct_rated_opponents": 210, "draws": 161, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:56Z", "losses": 117, "max_score": 76.32595670280091, "measured_at": null, "min_score": 26.60687800872694, "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 420, "rating_method": "sequential_elo", "raw_elo": 1526.0659801878735, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 45.15308829494262, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 142 }, { "admitted_plugins": 8, "attempted_matches": 438, "capped_draws": 53, "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": 0.158095, "min": 0.108735, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 11 }, "run_count": 8, "token_priced_attempt_count": 11, "total": 1.3395199999999998 }, "codegen_evaluated_cells": 8, "conditional_success_score": 41.99986875925433, "contributing_entrants": null, "distinct_rated_opponents": 218, "draws": 185, "entry_count": 8, "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 }, "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": "2026-07-27T11:44:47Z", "losses": 121, "max_score": 51.6075528075571, "measured_at": null, "min_score": 30.140455882095676, "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 438, "rating_method": "sequential_elo", "raw_elo": 1494.876673320847, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 41.99986875925433, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 132 }, { "admitted_plugins": 15, "attempted_matches": 490, "capped_draws": 80, "codegen_cost_usd": { "admitted_cell_count": 15, "cell_count": 8, "cost_basis_counts": { "provider_reported": 32 }, "evidence_basis": "Provider-reported", "failed_cell_count": 1, "max": 0.3926418, "mean": 0.31750829999999997, "median": 0.32150055, "min": 0.2298153, "recorded_attempt_count": 32, "run_count": 16, "total": 5.0801327999999994 }, "codegen_evaluated_cells": 16, "conditional_success_score": 42.25836257311796, "contributing_entrants": null, "distinct_rated_opponents": 245, "draws": 349, "entry_count": 25, "failed_game_aliases": [ "GB2-05" ], "first_pass_admitted": 1, "first_pass_rate": 0.0625, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:44:47Z", "losses": 201, "max_score": 67.21194886050958, "measured_at": null, "min_score": 20.580987520067197, "model_code_failure_rate": 0.0625, "model_code_failures": 1, "model_display_name": "Kimi K3", "model_slug": "moonshotai-kimi-k3", "plugin_success_rate": 0.9375, "provider": "Moonshot", "provider_key": "moonshotai", "rank": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 490, "rating_method": "sequential_elo", "raw_elo": 1525.4769490451797, "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" }, "repaired_admitted": 14, "repaired_rate": 0.875, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 41.58201053424288, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 245 }, { "admitted_plugins": 7, "attempted_matches": 402, "capped_draws": 65, "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": 0.21477375, "mean": 0.17756265624999998, "median": 0.17285124999999998, "min": 0.1418975, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 1.42050125 }, "codegen_evaluated_cells": 8, "conditional_success_score": 42.75066336563581, "contributing_entrants": null, "distinct_rated_opponents": 201, "draws": 136, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:44:47Z", "losses": 135, "max_score": 57.44029280728862, "measured_at": null, "min_score": 27.25028757645839, "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 402, "rating_method": "sequential_elo", "raw_elo": 1488.849954910172, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 41.34708256937608, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 131 }, { "admitted_plugins": 6, "attempted_matches": 366, "capped_draws": 45, "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": 0.03731, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 0.390976 }, "codegen_evaluated_cells": 8, "conditional_success_score": 43.922090004004865, "contributing_entrants": null, "distinct_rated_opponents": 183, "draws": 99, "entry_count": 6, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:44Z", "losses": 132, "max_score": 56.714061176471255, "measured_at": null, "min_score": 27.89874606250913, "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 366, "rating_method": "sequential_elo", "raw_elo": 1502.139772568575, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 40.87411037964668, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 135 }, { "admitted_plugins": 7, "attempted_matches": 216, "capped_draws": 27, "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": 0.121855, "mean": 0.09110296875, "median": 0.09280125, "min": 0.0343775, "recorded_attempt_count": 15, "run_count": 8, "total": 0.7288237499999999 }, "codegen_evaluated_cells": 8, "conditional_success_score": 41.59858019912202, "contributing_entrants": null, "distinct_rated_opponents": 108, "draws": 156, "entry_count": 14, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:36:38Z", "losses": 136, "max_score": 67.56797718896486, "measured_at": null, "min_score": 28.574021625817625, "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 216, "rating_method": "sequential_elo", "raw_elo": 1516.4342901702864, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 40.23282435529362, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 6, "attempted_matches": 168, "capped_draws": 27, "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": 0.0276132876, "recorded_attempt_count": 17, "run_count": 8, "total": 1.0777302952 }, "codegen_evaluated_cells": 8, "conditional_success_score": 42.76582870039201, "contributing_entrants": null, "distinct_rated_opponents": 84, "draws": 84, "entry_count": 11, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:51Z", "losses": 154, "max_score": 61.09711900072354, "measured_at": null, "min_score": 25.71921399965224, "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 168, "rating_method": "sequential_elo", "raw_elo": 1505.7383432287304, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 39.798087992112826, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 136 }, { "admitted_plugins": 23, "attempted_matches": 1315, "capped_draws": 172, "codegen_cost_usd": { "admitted_cell_count": 23, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 26 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 1, "max": 0.29749325000000004, "mean": 0.24155631250000004, "median": 0.24021375, "min": 0.17873725, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 26 }, "run_count": 24, "token_priced_attempt_count": 26, "total": 5.7973515 }, "codegen_evaluated_cells": 24, "conditional_success_score": 39.63048604415998, "contributing_entrants": null, "distinct_rated_opponents": 658, "draws": 485, "entry_count": 23, "failed_game_aliases": [ "GB2-06" ], "first_pass_admitted": 22, "first_pass_rate": 0.9166666666666666, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:44:52Z", "losses": 433, "max_score": 48.172020366997366, "measured_at": null, "min_score": 27.50563948445921, "model_code_failure_rate": 0.041666666666666664, "model_code_failures": 1, "model_display_name": "GPT-5.4 Mini", "model_slug": "gpt-5-4-mini", "plugin_success_rate": 0.9583333333333334, "provider": "OpenAI", "provider_key": "openai", "rank": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1315, "rating_method": "sequential_elo", "raw_elo": 1489.1305502122211, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.041666666666666664, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 39.21105679311512, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 397 }, { "admitted_plugins": 7, "attempted_matches": 416, "capped_draws": 52, "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": 0.132112, "mean": 0.0780535, "median": 0.06797, "min": 0.05673, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 0.624428 }, "codegen_evaluated_cells": 8, "conditional_success_score": 39.48455480226403, "contributing_entrants": null, "distinct_rated_opponents": 208, "draws": 137, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:58Z", "losses": 134, "max_score": 50.00396058789727, "measured_at": null, "min_score": 27.396699029090957, "model_code_failure_rate": 0.125, "model_code_failures": 1, "model_display_name": "Claude Sonnet 5", "model_slug": "claude-sonnet-5", "plugin_success_rate": 0.875, "provider": "Anthropic", "provider_key": "anthropic", "rank": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 416, "rating_method": "sequential_elo", "raw_elo": 1480.0737582799902, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 38.18820619603701, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 145 }, { "admitted_plugins": 6, "attempted_matches": 220, "capped_draws": 32, "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": 40.879144070193625, "contributing_entrants": null, "distinct_rated_opponents": 110, "draws": 140, "entry_count": 12, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:36:31Z", "losses": 122, "max_score": 58.39911627396981, "measured_at": null, "min_score": 27.02024765518864, "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 220, "rating_method": "sequential_elo", "raw_elo": 1500.1500481014182, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 38.042330107656966, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 12, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 12, "cell_count": 8, "cost_basis_counts": { "provider_reported": 32 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.04649778, "mean": 0.039593841, "median": 0.039509778, "min": 0.030762138, "recorded_attempt_count": 32, "run_count": 16, "total": 0.6335014560000001 }, "codegen_evaluated_cells": 16, "conditional_success_score": 39.55776475771556, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": 126, "entry_count": 12, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-26T05:11:55Z", "losses": 198, "max_score": 51.35463436894605, "measured_at": null, "min_score": 19.697931844478177, "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1455.471148029714, "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" }, "repaired_admitted": 12, "repaired_rate": 0.75, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 36.812648098747886, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 162 }, { "admitted_plugins": 8, "attempted_matches": 246, "capped_draws": 30, "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": 0.4852845999999999 }, "codegen_evaluated_cells": 8, "conditional_success_score": 36.60929744604539, "contributing_entrants": null, "distinct_rated_opponents": 123, "draws": 178, "entry_count": 16, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:48:47Z", "losses": 161, "max_score": 53.83120272886001, "measured_at": null, "min_score": 26.493587534338452, "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 246, "rating_method": "sequential_elo", "raw_elo": 1479.0876467501992, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 8, "repaired_rate": 1.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 36.60929744604539, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 151 }, { "admitted_plugins": 6, "attempted_matches": 180, "capped_draws": 2, "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": 37.9674466886763, "contributing_entrants": null, "distinct_rated_opponents": 90, "draws": 95, "entry_count": 12, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:03:48Z", "losses": 139, "max_score": 47.67871891237462, "measured_at": null, "min_score": 24.01242101325399, "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 180, "rating_method": "sequential_elo", "raw_elo": 1505.934469262074, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 35.33269037618208, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 128 }, { "admitted_plugins": 16, "attempted_matches": 936, "capped_draws": 90, "codegen_cost_usd": { "admitted_cell_count": 16, "cell_count": 8, "cost_basis_counts": { "provider_reported": 32 }, "evidence_basis": "Provider-reported", "max": 0.03261155, "mean": 0.02559155625, "median": 0.02516155, "min": 0.017927, "recorded_attempt_count": 32, "run_count": 16, "total": 0.4094649 }, "codegen_evaluated_cells": 16, "conditional_success_score": 34.578316108190634, "contributing_entrants": null, "distinct_rated_opponents": 466, "draws": 344, "entry_count": 15, "failed_game_aliases": [], "first_pass_admitted": 1, "first_pass_rate": 0.0625, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:31:38Z", "losses": 331, "max_score": 49.78746785854181, "measured_at": null, "min_score": 17.279603403559378, "model_code_failure_rate": 0.0, "model_code_failures": 0, "model_display_name": "Gemini 3.5 Flash Lite", "model_slug": "google-gemini-3-5-flash-lite", "plugin_success_rate": 1.0, "provider": "Google", "provider_key": "google", "rank": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 930, "rating_method": "sequential_elo", "raw_elo": 1434.0689168288116, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": 15, "repaired_rate": 0.9375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 34.578316108190634, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 255 }, { "admitted_plugins": 11, "attempted_matches": 698, "capped_draws": 33, "codegen_cost_usd": { "admitted_cell_count": 11, "cell_count": 8, "cost_basis_counts": { "provider_reported": 37 }, "evidence_basis": "Provider-reported", "failed_cell_count": 5, "max": 0.07934969, "mean": 0.053583788125, "median": 0.0553142075, "min": 0.02549349, "recorded_attempt_count": 37, "run_count": 16, "total": 0.85734061 }, "codegen_evaluated_cells": 16, "conditional_success_score": 36.467283143076706, "contributing_entrants": null, "distinct_rated_opponents": 349, "draws": 183, "entry_count": 11, "failed_game_aliases": [ "GB2-02", "GB2-03", "GB2-06", "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:31:22Z", "losses": 285, "max_score": 53.3592866591907, "measured_at": null, "min_score": 29.420591696289264, "model_code_failure_rate": 0.3125, "model_code_failures": 5, "model_display_name": "Inkling", "model_slug": "thinkingmachines-inkling", "plugin_success_rate": 0.6875, "provider": "Other", "provider_key": "other", "rank": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 698, "rating_method": "sequential_elo", "raw_elo": 1456.6485324874122, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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" }, "repaired_admitted": 11, "repaired_rate": 0.6875, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 33.20638391452173, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 230 }, { "admitted_plugins": 7, "attempted_matches": 368, "capped_draws": 67, "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": 0.001130258, "recorded_attempt_count": 16, "run_count": 8, "total": 0.01972526 }, "codegen_evaluated_cells": 8, "conditional_success_score": 33.28749406524547, "contributing_entrants": null, "distinct_rated_opponents": 184, "draws": 173, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:44:30Z", "losses": 112, "max_score": 38.85920360288856, "measured_at": null, "min_score": 28.976047880768927, "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 368, "rating_method": "sequential_elo", "raw_elo": 1440.504410376032, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 32.1946060549241, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 83 }, { "admitted_plugins": 11, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 11, "cell_count": 8, "cost_basis_counts": { "provider_reported": 22 }, "evidence_basis": "Provider-reported", "failed_cell_count": 3, "max": 0.00596013, "mean": 0.0023956312500000004, "median": 0.00186283, "min": 0.00105702, "recorded_attempt_count": 22, "run_count": 14, "total": 0.03542156 }, "codegen_evaluated_cells": 14, "conditional_success_score": 33.49075006569608, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": 223, "entry_count": 11, "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 }, "infra_excluded_game_aliases": [ "GB2-04", "GB2-06" ], "infra_failures_excluded": 2, "is_recent_addition": false, "last_measured_at": "2026-07-26T04:30:24Z", "losses": 140, "max_score": 40.298818357212, "measured_at": null, "min_score": 26.335060663959837, "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1451.4196186479696, "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" }, "repaired_admitted": 4, "repaired_rate": 0.2857142857142857, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 31.531239011473826, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 93 }, { "admitted_plugins": 4, "attempted_matches": 130, "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": 36.230230619845194, "contributing_entrants": null, "distinct_rated_opponents": 65, "draws": 47, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [ "GB2-01" ], "infra_failures_excluded": 1, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:05:52Z", "losses": 108, "max_score": 43.06115710405442, "measured_at": null, "min_score": 29.15567824497275, "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 130, "rating_method": "sequential_elo", "raw_elo": 1456.4764198441117, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 4, "repaired_rate": 0.5714285714285714, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 31.500074891654457, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 83 }, { "admitted_plugins": 25, "attempted_matches": 1484, "capped_draws": 148, "codegen_cost_usd": { "admitted_cell_count": 25, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 49 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 7, "max": 0.036200562500000005, "mean": 0.024352715625, "median": 0.02520601875, "min": 0.0165820625, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 49 }, "run_count": 32, "token_priced_attempt_count": 49, "total": 0.7792869 }, "codegen_evaluated_cells": 32, "conditional_success_score": 33.32297233861824, "contributing_entrants": null, "distinct_rated_opponents": 743, "draws": 411, "entry_count": 25, "failed_game_aliases": [ "GB2-02", "GB2-03", "GB2-04", "GB2-08" ], "first_pass_admitted": 13, "first_pass_rate": 0.40625, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:44:47Z", "losses": 669, "max_score": 54.484864054652334, "measured_at": null, "min_score": 19.139574631625756, "model_code_failure_rate": 0.21875, "model_code_failures": 7, "model_display_name": "GPT-5.4 Nano", "model_slug": "gpt-5-4-nano", "plugin_success_rate": 0.78125, "provider": "OpenAI", "provider_key": "openai", "rank": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1484, "rating_method": "sequential_elo", "raw_elo": 1435.8363111239446, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 12, "repaired_rate": 0.375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 31.32861821186002, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 404 }, { "admitted_plugins": 6, "attempted_matches": 176, "capped_draws": 25, "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": 32.26358588454963, "contributing_entrants": null, "distinct_rated_opponents": 88, "draws": 110, "entry_count": 12, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:47Z", "losses": 142, "max_score": 42.997436567986185, "measured_at": null, "min_score": 19.858838132294075, "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1443.823114057231, "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": "other", "provider_model": "cohere/north-mini-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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 30.02464979621979, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 98 }, { "admitted_plugins": 5, "attempted_matches": 298, "capped_draws": 56, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 19 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.0445032, "mean": 0.03204184375, "median": 0.0312573, "min": 0.0200767, "recorded_attempt_count": 19, "run_count": 9, "total": 0.2854256 }, "codegen_evaluated_cells": 9, "conditional_success_score": 33.72406167819707, "contributing_entrants": null, "distinct_rated_opponents": 149, "draws": 112, "entry_count": 5, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:38Z", "losses": 110, "max_score": 59.81864880409941, "measured_at": null, "min_score": 5.146710224123554, "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 298, "rating_method": "sequential_elo", "raw_elo": 1430.6490408549776, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 5, "repaired_rate": 0.5555555555555556, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 29.11533212995305, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 76 }, { "admitted_plugins": 15, "attempted_matches": 476, "capped_draws": 45, "codegen_cost_usd": { "admitted_cell_count": 15, "cell_count": 8, "cost_basis_counts": { "provider_reported": 46 }, "evidence_basis": "Provider-reported", "failed_cell_count": 6, "max": 0.02904086, "mean": 0.020196066154166664, "median": 0.0210709803, "min": 0.0085050301, "recorded_attempt_count": 46, "run_count": 21, "total": 0.426437947 }, "codegen_evaluated_cells": 21, "conditional_success_score": 30.35065853930814, "contributing_entrants": null, "distinct_rated_opponents": 238, "draws": 375, "entry_count": 30, "failed_game_aliases": [ "GB2-01", "GB2-03", "GB2-06", "GB2-08" ], "first_pass_admitted": 1, "first_pass_rate": 0.047619047619047616, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [ "GB2-03", "GB2-06", "GB2-07" ], "infra_failures_excluded": 3, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:44Z", "losses": 313, "max_score": 38.75915984031178, "measured_at": null, "min_score": 25.89649759084934, "model_code_failure_rate": 0.2857142857142857, "model_code_failures": 6, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": 0.7142857142857143, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 476, "rating_method": "sequential_elo", "raw_elo": 1451.7143963431668, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 14, "repaired_rate": 0.6666666666666666, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 27.902049817221116, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 236 }, { "admitted_plugins": 7, "attempted_matches": 214, "capped_draws": 30, "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": 0.09705768, "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": 28.831135463657088, "contributing_entrants": null, "distinct_rated_opponents": 107, "draws": 157, "entry_count": 14, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:47Z", "losses": 177, "max_score": 44.83748928548472, "measured_at": null, "min_score": 12.243419652002428, "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": 214, "rating_method": "sequential_elo", "raw_elo": 1421.2178272559431, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 7, "repaired_rate": 0.875, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 27.884557682511353, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 86 }, { "admitted_plugins": 6, "attempted_matches": 344, "capped_draws": 54, "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": 0.0149315, "mean": 0.00915140625, "median": 0.00943475, "min": 0.00402875, "recorded_attempt_count": 16, "run_count": 8, "total": 0.07321125 }, "codegen_evaluated_cells": 8, "conditional_success_score": 29.652763827122897, "contributing_entrants": null, "distinct_rated_opponents": 172, "draws": 90, "entry_count": 6, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:44:43Z", "losses": 154, "max_score": 42.33396509337835, "measured_at": null, "min_score": 5.363284090316728, "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 344, "rating_method": "sequential_elo", "raw_elo": 1390.1487813771837, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 4, "repaired_rate": 0.5, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 27.59500610332754, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 100 }, { "admitted_plugins": 5, "attempted_matches": 152, "capped_draws": 10, "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": 0.10247140625, "median": 0.113468875, "min": 0.061553, "recorded_attempt_count": 17, "run_count": 8, "total": 0.8197712500000001 }, "codegen_evaluated_cells": 8, "conditional_success_score": 27.98588259282322, "contributing_entrants": null, "distinct_rated_opponents": 76, "draws": 49, "entry_count": 10, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:36:40Z", "losses": 168, "max_score": 40.05712610425944, "measured_at": null, "min_score": 3.452798895447958, "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 152, "rating_method": "sequential_elo", "raw_elo": 1394.6530751194732, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 24.88335939329212, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 79 }, { "admitted_plugins": 16, "attempted_matches": 664, "capped_draws": 149, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 332, "draws": 245, "entry_count": 16, "failed_game_aliases": [], "first_pass_admitted": null, "first_pass_rate": null, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:55:02Z", "losses": 192, "max_score": 68.70041680687149, "measured_at": null, "min_score": 24.41934796442663, "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": "provisional", "rated_matches": 664, "rating_method": "sequential_elo", "raw_elo": 1524.646156720068, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 43.93076557633315, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 227 }, { "admitted_plugins": 4, "attempted_matches": 214, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 4, "cell_count": 8, "cost_basis_counts": { "provider_reported": 17 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.0711619, "mean": 0.0371769625, "median": 0.029592175, "min": 0.02387735, "recorded_attempt_count": 17, "run_count": 8, "total": 0.2974157 }, "codegen_evaluated_cells": 8, "conditional_success_score": 40.98023139587708, "contributing_entrants": null, "distinct_rated_opponents": 107, "draws": 92, "entry_count": 4, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:23:02Z", "losses": 64, "max_score": 53.536938067285334, "measured_at": null, "min_score": 32.827810893590744, "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": 214, "rating_method": "sequential_elo", "raw_elo": 1496.2164258090877, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": 4, "repaired_rate": 0.5, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 34.460129677060756, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugins": 14, "attempted_matches": 576, "capped_draws": 104, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 288, "draws": 216, "entry_count": 14, "failed_game_aliases": [], "first_pass_admitted": null, "first_pass_rate": null, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:48:17Z", "losses": 228, "max_score": 51.48147323629893, "measured_at": null, "min_score": 24.11930639666456, "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": "provisional", "rated_matches": 576, "rating_method": "sequential_elo", "raw_elo": 1447.304417416557, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 34.036578645771186, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 132 }, { "admitted_plugins": 7, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 7, "cell_count": 8, "cost_basis_counts": { "provider_reported": 34 }, "evidence_basis": "Provider-reported", "failed_cell_count": 8, "max": 0.0, "mean": 0.0, "median": 0.0, "min": 0.0, "recorded_attempt_count": 34, "run_count": 15, "total": 0.0 }, "codegen_evaluated_cells": 15, "conditional_success_score": 36.361429751934864, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": 84, "entry_count": 7, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "GB2-05", "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 }, "infra_excluded_game_aliases": [ "GB2-05" ], "infra_failures_excluded": 1, "is_recent_addition": false, "last_measured_at": "2026-07-26T04:32:32Z", "losses": 130, "max_score": 42.89789158042775, "measured_at": null, "min_score": 29.824967923441967, "model_code_failure_rate": 0.5333333333333333, "model_code_failures": 8, "model_display_name": "Ling 3.0 Flash", "model_slug": "inclusionai-ling-3-0-flash", "plugin_success_rate": 0.4666666666666667, "provider": "InclusionAI", "provider_key": "inclusionai", "rank": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "provisional", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1407.246967886118, "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": 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" }, "repaired_admitted": 7, "repaired_rate": 0.4666666666666667, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 30.053333230294538, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": null, "unilateral_faults": 0, "wins": 68 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:25:45Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1819.728353888386, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 89.02948337376621, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 47 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T11:25:35Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1661.6976408495564, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 68.52383229044648, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 36 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 24, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 24, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:25:54Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1653.411765004077, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 67.56620389662746, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 23 }, { "admitted_plugins": 3, "attempted_matches": 208, "capped_draws": 25, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 104, "draws": 25, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 67, "max_score": null, "measured_at": "2026-07-27T11:25:15Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 208, "rating_method": "sequential_elo", "raw_elo": 1631.9565756398863, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 65.32770242067362, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 16.089767264777418, "unilateral_faults": 0, "wins": 116 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 8, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 8, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T11:21:33Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1631.9779985185817, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 65.00304603642252, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 31 }, { "admitted_plugins": 2, "attempted_matches": 98, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 49, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 34, "max_score": null, "measured_at": "2026-07-27T10:30:27Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 98, "rating_method": "sequential_elo", "raw_elo": 1619.2961858016197, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 62.55535735493004, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 26.97128781498596, "unilateral_faults": 0, "wins": 57 }, { "admitted_plugins": 0, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T10:26:46Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1612.48039153947, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 61.09711900072354, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 22 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:23:03Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1589.1789388885927, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 58.990116931190066, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 29 }, { "admitted_plugins": 2, "attempted_matches": 120, "capped_draws": 33, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 60, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T10:36:10Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 120, "rating_method": "sequential_elo", "raw_elo": 1581.1012071463724, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 58.29507221734059, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 61 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 38, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T11:21:38Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1578.7755636434526, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.76408091303755, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 15 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:17:18Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1521.3936825716696, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.19447975472116, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-26T01:14:31Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1527.987432545009, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.94278083109678, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 16 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 5, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 20, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:31:19Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1527.58898800444, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.426447239287874, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 38.812854461075986, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 14, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 14, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T11:25:54Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1508.9996053111847, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.14708051635627, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 2, "attempted_matches": 60, "capped_draws": 30, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 30, "draws": 65, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:22:16Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1521.630336835687, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.37070779104473, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 41.534862397692415, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 2, "attempted_matches": 126, "capped_draws": 31, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 63, "draws": 31, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 55, "max_score": null, "measured_at": "2026-07-27T11:31:26Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 126, "rating_method": "sequential_elo", "raw_elo": 1503.158468494203, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.3336953705786, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 18.8015810723003, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 20, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 20, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T11:25:45Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1500.156493815032, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.5626764936281, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 18 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 3, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 20, "draws": 10, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:33:29Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1507.9573663660651, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 46.577603476802054, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 41.71727501641449, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 9, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T11:17:05Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1483.905475102522, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.19928208402567, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:33:08Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1495.4492714651392, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.64799882230341, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 44.67073949561819, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 3, "attempted_matches": 194, "capped_draws": 32, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 97, "draws": 32, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 88, "max_score": null, "measured_at": "2026-07-27T11:25:52Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 194, "rating_method": "sequential_elo", "raw_elo": 1467.8106521935588, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.80108841581784, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 18.28106122889297, "unilateral_faults": 0, "wins": 74 }, { "admitted_plugins": 2, "attempted_matches": 84, "capped_draws": 25, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 42, "draws": 25, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T10:26:48Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 84, "rating_method": "sequential_elo", "raw_elo": 1478.9713630017695, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.773337420402555, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 22 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 29, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 29, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 16, "max_score": null, "measured_at": "2026-07-27T10:33:16Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1458.4305805417964, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.26595649843005, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 13 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T11:25:46Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1450.988870016457, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.41203641046077, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 27 }, { "admitted_plugins": 2, "attempted_matches": 88, "capped_draws": 35, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 44, "draws": 35, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:47:56Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 88, "rating_method": "sequential_elo", "raw_elo": 1455.6399619899837, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.92380669690927, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 2, "attempted_matches": 74, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 37, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 69, "max_score": null, "measured_at": "2026-07-27T11:17:15Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1457.4978861248828, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.22743264582813, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 39.81642880532208, "unilateral_faults": 0, "wins": 56 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 18, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 18, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T11:22:15Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1406.1009817298916, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.358279790014166, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 16 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 24, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:25:46Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1413.8795717766495, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.19470044445362, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 43.40903824311957, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 4, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 40, "max_score": null, "measured_at": "2026-07-27T10:33:29Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1409.681447736922, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.92438548422537, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 2, "attempted_matches": 122, "capped_draws": 33, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 61, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 49, "max_score": null, "measured_at": "2026-07-27T11:26:27Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 122, "rating_method": "sequential_elo", "raw_elo": 1381.0155302257313, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.38564662410492, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 19.7562594006596, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 15, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:21:50Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1359.6393456579792, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.205660998009655, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 14 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 8, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-26T02:18:41Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1351.2546228678034, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.010394711158984, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 9 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 14, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-26T02:12:15Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1301.4844814069097, "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": 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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 20.552351615993096, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 4, "attempted_matches": 228, "capped_draws": 51, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 114, "draws": 51, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 138, "max_score": null, "measured_at": "2026-07-27T11:25:52Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 228, "rating_method": "sequential_elo", "raw_elo": 1280.700601387579, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 19.139574631625756, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 21.96682519692495, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugins": 2, "attempted_matches": 98, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 49, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-27T09:25:43Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 98, "rating_method": "sequential_elo", "raw_elo": 1630.3875789807648, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 63.94985004999732, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 26.97128781498596, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 28, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T10:43:03Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1624.075614202798, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 63.51723403185436, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 21 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 25, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T10:42:56Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1554.6276258057092, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 46.92274071038185, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 22 }, { "admitted_plugins": 2, "attempted_matches": 132, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 66, "draws": 81, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T10:43:03Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 132, "rating_method": "sequential_elo", "raw_elo": 1542.432769124338, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.63145274557937, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 18.087190646312703, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 30, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T10:39:40Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1534.4980840240307, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.89639389555927, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 14 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T11:18:10Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1499.278211372801, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.25253493848372, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 7 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 49, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T11:23:02Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1497.5007403786417, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.827810893590744, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1 }, { "admitted_plugins": 2, "attempted_matches": 128, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 64, "draws": 120, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T11:23:13Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 128, "rating_method": "sequential_elo", "raw_elo": 1486.2711131042715, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.17726639024936, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T11:26:34Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1489.9472910874329, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.022925443196662, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1 }, { "admitted_plugins": 1, "attempted_matches": 50, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 0, "max_score": null, "measured_at": "2026-07-27T10:35:34Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1491.9181454193697, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.997988769059855, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T10:43:03Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1487.2623907567247, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.140455882095676, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 3, "attempted_matches": 156, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 78, "draws": 144, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:26:42Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 156, "rating_method": "sequential_elo", "raw_elo": 1487.0053737211565, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.047425320937624, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 25.095677040127953, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 63, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T11:18:18Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1476.5603955656177, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.205662826109684, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T11:23:13Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1484.5879724595852, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.976047880768927, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 3, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 82, "draws": 149, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:26:38Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1481.0444737034147, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.875429548217255, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 23.77555789204983, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 128, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 64, "draws": 123, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T11:26:38Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 128, "rating_method": "sequential_elo", "raw_elo": 1476.427219156717, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.820870760406777, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 18.289400506511907, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-26T02:19:22Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1489.1522376403848, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.79387773495653, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 14, "draws": 63, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T10:35:34Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 28, "rating_method": "sequential_elo", "raw_elo": 1495.4643675592058, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.702345229467554, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 42.70587299553475, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 53, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T10:38:09Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1498.8227626605349, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.574021625817625, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 47.5751600509567, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 52, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T10:39:38Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1479.6156043304468, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.554184291069387, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 79, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-26T01:24:29Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1487.3145592583064, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.354767224454108, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 1, "attempted_matches": 26, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 13, "draws": 52, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T09:03:06Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 26, "rating_method": "sequential_elo", "raw_elo": 1496.234358452679, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.632718734896457, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 49.26384793916254, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 39, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T10:39:37Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1477.1586139699823, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.60687800872694, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 3, "attempted_matches": 84, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 42, "draws": 157, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T10:39:37Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 84, "rating_method": "sequential_elo", "raw_elo": 1490.1593860965586, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.396318186763295, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 48.13805601369197, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 59, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T09:17:42Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1462.112751652437, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.753419845975525, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T11:26:19Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1470.8448216282686, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.41934796442663, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 2, "attempted_matches": 74, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 37, "draws": 68, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T11:23:02Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1472.025070521855, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.11930639666456, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 37.38178527761111, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:39:38Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1477.4089183486803, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.01242101325399, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 44.67073949561819, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-25T18:00:56Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1466.728730509414, "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": 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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 23.435814126241773, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 2 }, { "admitted_plugins": 1, "attempted_matches": 26, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 13, "draws": 56, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T07:52:19Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 26, "rating_method": "sequential_elo", "raw_elo": 1473.372937630626, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.896721550174966, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 45.462269258808135, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 2, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 31, "draws": 94, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T10:43:03Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1488.0188021214274, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 20.580987520067197, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 55.91958998388486, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 80, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 40, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-26T05:18:21Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1776.563151472152, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 91.93118700577348, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 65 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 12, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:52:52Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1594.5085265402074, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 61.60004691193783, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 1, "attempted_matches": 50, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 14, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T11:52:57Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1586.8467498305283, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 60.91553236200583, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 2, "attempted_matches": 104, "capped_draws": 5, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 52, "draws": 37, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T11:10:15Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 104, "rating_method": "sequential_elo", "raw_elo": 1559.337130627261, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 56.435256830019185, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 24.966995223862348, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 15, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:48:17Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1546.9358887216838, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.48147323629893, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 3, "attempted_matches": 156, "capped_draws": 16, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 78, "draws": 70, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T11:52:52Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 156, "rating_method": "sequential_elo", "raw_elo": 1525.3124264162536, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.60736443084445, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 25.479237126358175, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugins": 2, "attempted_matches": 102, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 51, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:31:38Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 102, "rating_method": "sequential_elo", "raw_elo": 1520.5623366481875, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.78746785854181, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 25.597143087872503, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugins": 3, "attempted_matches": 136, "capped_draws": 29, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 68, "draws": 77, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:44:52Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 136, "rating_method": "sequential_elo", "raw_elo": 1514.5537109582262, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.172020366997366, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 30.01758738954685, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 2, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 19, "draws": 20, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T11:44:47Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1530.631146017652, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.41563774645095, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 55.70080376775669, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 24, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T11:44:47Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1504.641480334261, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.64189418693135, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 13, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-26T01:22:06Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1487.6875843006812, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.04022494558611, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 14 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 15, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 32, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T11:44:52Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1487.0489962766576, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.932146636436144, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 6, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 15, "draws": 19, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T11:30:40Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1483.8175424040835, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.79896136680666, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 19, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T10:03:28Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1471.7215759387857, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.338045883793995, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 8 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 35, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 34, "max_score": null, "measured_at": "2026-07-26T03:31:46Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1467.727157847934, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.298818357212, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 29.63358145932378, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 1, "attempted_matches": 26, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 13, "draws": 30, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T11:36:40Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 26, "rating_method": "sequential_elo", "raw_elo": 1486.0822555481582, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.05712610425944, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 54.36252243246881, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 20, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 10, "draws": 22, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:48:47Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 20, "rating_method": "sequential_elo", "raw_elo": 1484.771748750963, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.653453444576584, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 55.70579806569183, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 5, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 23, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:52:56Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1461.662536911419, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.63559627801959, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 7 }, { "admitted_plugins": 1, "attempted_matches": 42, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 21, "draws": 26, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:44:41Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1435.8623185574695, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.51782318989246, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 5 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 28, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:44:30Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1431.961147134627, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.30664851641847, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 1, "attempted_matches": 22, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 11, "draws": 23, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:44:41Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 22, "rating_method": "sequential_elo", "raw_elo": 1435.792509312745, "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": "other", "provider_model": "cohere/north-mini-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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.48623719869417, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 54.80243805853167, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 24, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T09:28:28Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1411.064865920198, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.973667967146064, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 24, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:52:56Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1403.617820599916, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.256036000566052, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 11 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 24, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T10:53:10Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1566.7841216373108, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.32044382130511, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 17 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 39, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T10:53:02Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1548.729486332967, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 46.07577553411435, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 14 }, { "admitted_plugins": 3, "attempted_matches": 174, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 87, "draws": 116, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T10:58:56Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 174, "rating_method": "sequential_elo", "raw_elo": 1549.3135275728098, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 46.0004231200324, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 21.47132379806021, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 2, "attempted_matches": 128, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 64, "draws": 77, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T10:53:09Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 128, "rating_method": "sequential_elo", "raw_elo": 1545.9269827773976, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.804624380131344, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 18.466769200052298, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugins": 2, "attempted_matches": 100, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 50, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T10:48:26Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 100, "rating_method": "sequential_elo", "raw_elo": 1538.2157242898909, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.019463779962486, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 26.304426701457977, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 32, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:53:12Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1535.795958549268, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.75642364948741, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 50, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 42, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T08:31:20Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1526.1505400202454, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.6224615828462, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 59, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T10:43:48Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1512.834046928935, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.08847356683884, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 2 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 40, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T10:53:01Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1513.1147492207922, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.809666551358085, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 49, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T08:29:49Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1510.4667796354577, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.61690227136209, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 8 }, { "admitted_plugins": 3, "attempted_matches": 200, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 100, "draws": 145, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 27, "max_score": null, "measured_at": "2026-07-27T10:58:56Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 200, "rating_method": "sequential_elo", "raw_elo": 1504.06188219994, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.60021583373031, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 17.617608894322856, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 22, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T10:53:10Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1518.91404152128, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.7846857638282, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 47.5751600509567, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugins": 2, "attempted_matches": 130, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 63, "draws": 98, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T10:48:25Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 124, "rating_method": "sequential_elo", "raw_elo": 1489.3127842819954, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.401973606580675, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 19.250031750047626, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 2, "attempted_matches": 125, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 62, "draws": 83, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T10:45:29Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 124, "rating_method": "sequential_elo", "raw_elo": 1488.8990253241063, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.32049946583581, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 23 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T10:43:48Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1489.7668442731074, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.15864897798004, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 1, "attempted_matches": 42, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 21, "draws": 36, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T07:29:08Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1497.0294371743323, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.82771565073253, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 32, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T10:03:17Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1487.5701896988592, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.47196362002854, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 2, "attempted_matches": 72, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 36, "draws": 35, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T10:43:48Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 72, "rating_method": "sequential_elo", "raw_elo": 1493.572395842094, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.17642355544414, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 38.53975118769762, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugins": 1, "attempted_matches": 24, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 12, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T10:50:03Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 24, "rating_method": "sequential_elo", "raw_elo": 1505.9919152699777, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.12887382515068, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 54.36252243246881, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 36, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T10:48:25Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1480.001540532111, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.70877457082836, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 2, "attempted_matches": 114, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 57, "draws": 87, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-27T10:51:30Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 114, "rating_method": "sequential_elo", "raw_elo": 1472.8755524653086, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.70360759272194, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 21.910536671832062, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 50, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 40, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T10:53:08Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1471.7037725606615, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.776397542600765, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 20, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 10, "draws": 43, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T08:27:58Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 20, "rating_method": "sequential_elo", "raw_elo": 1496.3916661363678, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.759754221251917, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 57.22830710326107, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:50:01Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1485.8821345908264, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.15567824497275, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 47.88193642139327, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T10:45:32Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1471.716990074414, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.177411381216853, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 22, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 11, "draws": 39, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T10:03:23Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 22, "rating_method": "sequential_elo", "raw_elo": 1487.659821181334, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.1378078235891, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 56.49112594673751, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 44, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T10:10:02Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1460.2028298284708, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.89874606250913, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 40, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T10:49:59Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1454.5510147312568, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.47820671040979, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 9 }, { "admitted_plugins": 1, "attempted_matches": 18, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 9, "draws": 35, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T10:10:04Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 18, "rating_method": "sequential_elo", "raw_elo": 1483.3259674335122, "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": "other", "provider_model": "cohere/north-mini-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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.71086962365695, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 60.027768011903404, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 2, "attempted_matches": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 38, "draws": 78, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:53:10Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1473.5659425899894, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.24443459360968, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 50.75459128937461, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 1, "attempted_matches": 22, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 11, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:49:59Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 22, "rating_method": "sequential_elo", "raw_elo": 1476.1836514200374, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.12081427726525, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 54.80243805853167, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 3, "attempted_matches": 86, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 43, "draws": 134, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T10:53:41Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 86, "rating_method": "sequential_elo", "raw_elo": 1469.7704001821894, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.89649759084934, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 48.19344896390418, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 36, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-26T04:32:32Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1450.768790271424, "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": 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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.61236711374963, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 28, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-26T04:07:10Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1431.6560449045471, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 20.80501417240327, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-26T03:03:30Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1429.2136617086594, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 19.697931844478177, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 36.39318729849085, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 2, "attempted_matches": 112, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 56, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:10:13Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 112, "rating_method": "sequential_elo", "raw_elo": 1790.4131145129454, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 79.52963881852078, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 84 }, { "admitted_plugins": 2, "attempted_matches": 146, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 73, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 54, "max_score": null, "measured_at": "2026-07-27T11:10:13Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 146, "rating_method": "sequential_elo", "raw_elo": 1705.221400737045, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 70.1276647758533, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 14.377800258513927, "unilateral_faults": 0, "wins": 92 }, { "admitted_plugins": 3, "attempted_matches": 214, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 107, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 75, "max_score": null, "measured_at": "2026-07-27T11:10:13Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 214, "rating_method": "sequential_elo", "raw_elo": 1699.4681950681795, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 69.34645655053502, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 15.361567975806963, "unilateral_faults": 0, "wins": 139 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:10:13Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1652.109166288075, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 63.117863543585464, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 37 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T11:03:48Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1639.493660691125, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 61.71380324937027, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 40 }, { "admitted_plugins": 2, "attempted_matches": 94, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 47, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 44, "max_score": null, "measured_at": "2026-07-27T11:08:03Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 94, "rating_method": "sequential_elo", "raw_elo": 1586.7624035224435, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 54.63527551118202, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 28.430533588759353, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:03:41Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1591.4510347559626, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.83120272886001, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 42.70587299553475, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T10:36:15Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1572.8040677708518, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.536938067285334, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T10:59:00Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1567.8741951513823, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.05626716087649, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 27 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:59:00Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1566.3786416398286, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.65540636850494, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 25 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:03:41Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1564.6835482433685, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.452932914118634, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 30 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:17:17Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1554.884848939414, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.6075528075571, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:07:34Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1525.8350202224913, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.32886155421666, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:03:42Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1525.7692733725237, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.12979094866205, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T11:03:48Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1544.0837274481669, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.67871891237462, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 47.88193642139327, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 27, "max_score": null, "measured_at": "2026-07-27T11:09:46Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1520.9036581003338, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.646494167430816, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 35 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T08:40:46Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1530.497151230373, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 46.176411006143624, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 46.62023516889464, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:07:38Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1497.821508842899, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.157076581963906, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 36 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 22, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:07:33Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1508.3722086805085, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.01048103554146, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 41.6303220574653, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:05:52Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1504.0748772526315, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.06115710405442, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 46.19324853318743, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 74, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 37, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 40, "max_score": null, "measured_at": "2026-07-27T10:25:28Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1469.3980693923404, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.99685872000467, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 34 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:09:47Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1469.150703841991, "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": "other", "provider_model": "cohere/north-mini-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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.36830859417666, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 41.18336395796551, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 44, "max_score": null, "measured_at": "2026-07-26T04:30:24Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1459.640319348581, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.9743540171584, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 33.41808305530269, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T11:04:04Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1447.33708487285, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.85920360288856, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 33 }, { "admitted_plugins": 2, "attempted_matches": 72, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 36, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 69, "max_score": null, "measured_at": "2026-07-27T10:17:43Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 72, "rating_method": "sequential_elo", "raw_elo": 1463.883778294188, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.75915984031178, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 40.974394715408586, "unilateral_faults": 0, "wins": 67 }, { "admitted_plugins": 4, "attempted_matches": 254, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 127, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 141, "max_score": null, "measured_at": "2026-07-27T11:17:17Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 254, "rating_method": "sequential_elo", "raw_elo": 1435.585169745014, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.5178295193274, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 18.59154576158009, "unilateral_faults": 0, "wins": 113 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 44, "max_score": null, "measured_at": "2026-07-26T01:24:50Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1443.580106809795, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.968215320622434, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 36 }, { "admitted_plugins": 3, "attempted_matches": 172, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 86, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 95, "max_score": null, "measured_at": "2026-07-27T11:07:24Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 172, "rating_method": "sequential_elo", "raw_elo": 1427.4966669312123, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.25256072815697, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 21.721842944692018, "unilateral_faults": 0, "wins": 77 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T11:05:50Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1515.0366203285198, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.24533485626138, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 69.22474682633933, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T08:38:42Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1409.8327711353909, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.31299675673494, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 40.86916081526379, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 2, "attempted_matches": 94, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 47, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 55, "max_score": null, "measured_at": "2026-07-27T11:04:08Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 94, "rating_method": "sequential_elo", "raw_elo": 1393.1588342212412, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.50995183297395, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 28.430533588759353, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugins": 2, "attempted_matches": 132, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 66, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 67, "max_score": null, "measured_at": "2026-07-27T11:08:00Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 132, "rating_method": "sequential_elo", "raw_elo": 1369.477572900474, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.739636786078208, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 17.355146918744417, "unilateral_faults": 0, "wins": 65 }, { "admitted_plugins": 2, "attempted_matches": 132, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 66, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 78, "max_score": null, "measured_at": "2026-07-27T11:06:11Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 132, "rating_method": "sequential_elo", "raw_elo": 1366.8065500421274, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.420591696289264, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 17.355146918744417, "unilateral_faults": 0, "wins": 54 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 44, "max_score": null, "measured_at": "2026-07-27T11:07:34Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1360.9092359313067, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.238020657975618, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T11:07:33Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1321.2599404656255, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 23.893026239049423, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 51, "max_score": null, "measured_at": "2026-07-27T11:09:47Z", "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": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1247.4219158546216, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 12.243419652002428, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 47.88193642139327, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T10:46:56Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1788.705954908835, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 90.34672640532096, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 1, "attempted_matches": 50, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T10:46:50Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1732.4144195081535, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 82.67382914279403, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugins": 2, "attempted_matches": 128, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 64, "draws": 14, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 36, "max_score": null, "measured_at": "2026-07-27T10:41:50Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 128, "rating_method": "sequential_elo", "raw_elo": 1704.3788148815706, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 79.77925593934339, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 78 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:52:51Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1681.0254506469776, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 76.32595670280091, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 36 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T10:44:49Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1667.5084391584408, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 74.1340312841928, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T10:44:46Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1646.4648905020276, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 71.02490499954271, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 2, "attempted_matches": 80, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 40, "draws": 10, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T10:41:40Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1634.4148964003216, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 68.70041680687149, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 44 }, { "admitted_plugins": 2, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 31, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 27, "max_score": null, "measured_at": "2026-07-27T11:36:38Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1628.3092646305531, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 67.21194886050958, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 40.6135880525129, "unilateral_faults": 0, "wins": 66 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:44:32Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1591.7478127385095, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 64.38321088344401, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 3, "attempted_matches": 200, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 100, "draws": 22, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 80, "max_score": null, "measured_at": "2026-07-27T11:30:11Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 200, "rating_method": "sequential_elo", "raw_elo": 1565.809397581451, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 61.32306059649945, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 17.516513567803994, "unilateral_faults": 0, "wins": 98 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 4, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T11:52:38Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1555.945264596268, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 59.81864880409941, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T10:41:09Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1566.8929275335172, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 58.39911627396981, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 46.19324853318743, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:52:51Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1560.571039169908, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.85138882139616, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 43.40903824311957, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 2, "attempted_matches": 120, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 60, "draws": 5, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 50, "max_score": null, "measured_at": "2026-07-27T11:44:32Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 120, "rating_method": "sequential_elo", "raw_elo": 1539.3980095984984, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.47045192344825, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 20.50235421223841, "unilateral_faults": 0, "wins": 65 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 10, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:36:33Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1533.5565018760735, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 56.714061176471255, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 4, "attempted_matches": 242, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 121, "draws": 17, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 120, "max_score": null, "measured_at": "2026-07-27T11:30:20Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 242, "rating_method": "sequential_elo", "raw_elo": 1516.80550194545, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 54.484864054652334, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 20.16006027106505, "unilateral_faults": 0, "wins": 105 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:36:38Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1516.5320737959407, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.48135378529035, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 38.53975118769762, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:36:36Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1498.859087874097, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.70853629281069, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 22 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T10:46:50Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1496.011348653353, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.455302113536305, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 4, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 41, "max_score": null, "measured_at": "2026-07-26T03:28:35Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1495.4573766623844, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.21027749681558, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 33.41808305530269, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 3, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:52:58Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1480.3349355924784, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.00396058789727, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 33 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:52:58Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1448.0809451241314, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.16477138641322, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:43:04Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1429.7879988349669, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.33396509337835, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T10:39:35Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1430.7493983829115, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.89186947333852, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 39.60745956276516, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 2, "attempted_matches": 122, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 61, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 69, "max_score": null, "measured_at": "2026-07-27T10:40:04Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 122, "rating_method": "sequential_elo", "raw_elo": 1409.7666921541868, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.2094045434509, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 19.7562594006596, "unilateral_faults": 0, "wins": 51 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-27T10:43:06Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1388.4103550666105, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.933715039786, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 20 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 34, "max_score": null, "measured_at": "2026-07-27T10:44:43Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1369.2947045902554, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.37659816081083, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 19 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 3, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 35, "max_score": null, "measured_at": "2026-07-27T10:44:50Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1384.079848744715, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.615449335199195, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 49.26384793916254, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T10:43:03Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1381.5813863174303, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.46194565997123, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 47.5751600509567, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 35, "max_score": null, "measured_at": "2026-07-27T10:36:18Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1356.7474097662753, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.17178175285869, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 27 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T10:46:50Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1379.3228938160337, "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": "other", "provider_model": "cohere/north-mini-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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.15982519048976, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 47.5751600509567, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T10:44:46Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1362.877850832631, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.529723961553977, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 42.25107233303306, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T10:43:01Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1364.522971792873, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.999309214021817, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 49.26384793916254, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 53, "max_score": null, "measured_at": "2026-07-26T02:18:39Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1343.802645127367, "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": 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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.824967923441967, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-26T02:14:14Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1337.3836752186996, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.966296840321345, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 13 }, { "admitted_plugins": 2, "attempted_matches": 82, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 41, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 52, "max_score": null, "measured_at": "2026-07-27T10:41:39Z", "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": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 82, "rating_method": "sequential_elo", "raw_elo": 1331.1083724223636, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.225170931660724, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 33.41808305530269, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 2, "attempted_matches": 106, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 53, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T10:36:03Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 106, "rating_method": "sequential_elo", "raw_elo": 1831.0772363583328, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 90.66753720750904, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 24.30013411033436, "unilateral_faults": 0, "wins": 82 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:09:44Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1721.3733595723618, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 76.52631679447857, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 41 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:05:51Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1655.5878327465305, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 67.93204374088673, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 37 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T11:09:45Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1667.5150915775343, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 67.56797718896486, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 40.86916081526379, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugins": 3, "attempted_matches": 206, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 102, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 76, "max_score": null, "measured_at": "2026-07-27T11:09:46Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 206, "rating_method": "sequential_elo", "raw_elo": 1638.8693146453372, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 66.36171022225238, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 16.603769221136574, "unilateral_faults": 0, "wins": 130 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T11:05:48Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1637.762905975935, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 65.72170653066799, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T08:36:03Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1613.924246727442, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 62.60740530517968, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 33 }, { "admitted_plugins": 3, "attempted_matches": 128, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 64, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 51, "max_score": null, "measured_at": "2026-07-27T11:55:02Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 128, "rating_method": "sequential_elo", "raw_elo": 1615.0897353689145, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 61.653545677315115, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 31.928056527532547, "unilateral_faults": 0, "wins": 77 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:05:45Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1571.1643984055847, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.44029280728862, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 41 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T10:15:39Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1563.3796006203124, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 56.004212916192515, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 34 }, { "admitted_plugins": 2, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 34, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 44, "max_score": null, "measured_at": "2026-07-27T11:05:45Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1573.87579650109, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.562434490225975, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 38.69173419161021, "unilateral_faults": 0, "wins": 64 }, { "admitted_plugins": 2, "attempted_matches": 130, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 65, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 63, "max_score": null, "measured_at": "2026-07-27T11:31:22Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 130, "rating_method": "sequential_elo", "raw_elo": 1540.3330460767777, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.3592866591907, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 17.8435026888779, "unilateral_faults": 0, "wins": 67 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T11:09:46Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1537.8619196179889, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.99215754691314, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T11:38:26Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1502.494574211802, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.65165422462213, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T11:17:13Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1486.9450008445583, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 46.43780435774322, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 36 }, { "admitted_plugins": 3, "attempted_matches": 189, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 95, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 104, "max_score": null, "measured_at": "2026-07-27T11:17:08Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1482.0610924621042, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.63424487271845, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 18.91847187152537, "unilateral_faults": 0, "wins": 85 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 35, "max_score": null, "measured_at": "2026-07-27T11:03:45Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1498.1567772201045, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.57473728904729, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 39.60745956276516, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T10:59:03Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1498.1236759239546, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.83748928548472, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 46.62023516889464, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T11:17:08Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1476.3023229705768, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.38532142418434, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 2, "attempted_matches": 136, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 68, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 56, "max_score": null, "measured_at": "2026-07-27T11:37:40Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 136, "rating_method": "sequential_elo", "raw_elo": 1470.4484547993857, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.37390326134637, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 16.461902543922633, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 41, "max_score": null, "measured_at": "2026-07-27T11:26:19Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1482.226825234452, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.82956786001692, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 36.39318729849085, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-27T11:09:43Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1481.7615272516564, "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": "other", "provider_model": "cohere/north-mini-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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.997436567986185, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 43.7735813706023, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 45, "max_score": null, "measured_at": "2026-07-26T01:23:46Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1473.4501921154751, "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": 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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.89789158042775, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 35 }, { "admitted_plugins": 2, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 63, "max_score": null, "measured_at": "2026-07-27T11:05:53Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1463.9651854578856, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.65095770356271, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 43.979783736733566, "unilateral_faults": 0, "wins": 63 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 22, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 36, "max_score": null, "measured_at": "2026-07-27T10:59:03Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1460.0772374862684, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.56507075019223, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 39.941634169259466, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T08:07:41Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1454.3672812155585, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.24214147038237, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 45.462269258808135, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugins": 2, "attempted_matches": 86, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 43, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 57, "max_score": null, "measured_at": "2026-07-27T11:26:19Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 86, "rating_method": "sequential_elo", "raw_elo": 1440.1690757297024, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.83162319473614, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 31.642442208147656, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 35, "max_score": null, "measured_at": "2026-07-27T10:17:46Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1449.4234555848543, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.65174334487914, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 44.9315472806888, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 27, "max_score": null, "measured_at": "2026-07-26T23:00:21Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1416.8015449056545, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.612092900151, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 27 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 41, "max_score": null, "measured_at": "2026-07-27T11:07:27Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1355.5092833564145, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.80729258947612, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 40.86916081526379, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-26T02:18:59Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1340.532812293546, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.53346036165865, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 10 }, { "admitted_plugins": 4, "attempted_matches": 233, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 117, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 175, "max_score": null, "measured_at": "2026-07-27T11:38:30Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 233, "rating_method": "sequential_elo", "raw_elo": 1304.2443438279372, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.14962114886749, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 21.353618598248712, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugins": 2, "attempted_matches": 126, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 63, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 77, "max_score": null, "measured_at": "2026-07-27T10:30:43Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 126, "rating_method": "sequential_elo", "raw_elo": 1264.8881004574012, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 17.279603403559378, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 18.755723064737715, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 46, "max_score": null, "measured_at": "2026-07-27T11:17:13Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1176.6504298057089, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 5.363284090316728, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 10 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 45, "max_score": null, "measured_at": "2026-07-27T11:09:47Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1172.4066172061932, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 5.146710224123554, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 17 }, { "admitted_plugins": 3, "attempted_matches": 186, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 93, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T10:46:49Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1814.1521582571097, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 84.85770377828395, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 19.53054898057647, "unilateral_faults": 0, "wins": 153 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T10:50:04Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1742.3401615411974, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 73.64139541154456, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 48 }, { "admitted_plugins": 2, "attempted_matches": 116, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 58, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 40, "max_score": null, "measured_at": "2026-07-27T11:04:07Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 116, "rating_method": "sequential_elo", "raw_elo": 1730.1736010828918, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 71.62324112334503, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 76 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 5, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 5, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T10:59:35Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1672.1128256209613, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 62.628672220103525, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 38 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T11:04:07Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1602.2012432700476, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.51149993427681, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 13, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-26T05:11:55Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1606.890781954458, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.35463436894605, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 25, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 25, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T11:44:43Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1541.4688058948389, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.65007148744865, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 15 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 5, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T10:41:07Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1544.324469670316, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.76998981781314, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugins": 3, "attempted_matches": 188, "capped_draws": 93, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 94, "draws": 93, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 48, "max_score": null, "measured_at": "2026-07-27T11:44:47Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1511.3185496845665, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.01038466859352, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 18.993268825260195, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 33, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T10:37:56Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1488.7884995268803, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.36207341877303, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 13 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 49, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 49, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T09:14:03Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1466.5807611762505, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.048681859229955, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 66, "capped_draws": 38, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T11:52:44Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1462.0021926743475, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.576018901450553, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 10 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 45, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T10:03:23Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1464.2474413129037, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.42690593498895, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3 }, { "admitted_plugins": 2, "attempted_matches": 88, "capped_draws": 50, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 44, "draws": 81, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:36:31Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 88, "rating_method": "sequential_elo", "raw_elo": 1472.7476833365188, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.422387009917625, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 32.006220619850886, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugins": 1, "attempted_matches": 72, "capped_draws": 25, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 36, "draws": 25, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:44:43Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 72, "rating_method": "sequential_elo", "raw_elo": 1457.7343014406704, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.232635390830257, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 23 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 20, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 37, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:30:20Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1481.8014648809944, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.066723518033452, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 46.19324853318743, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 21, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 21, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T10:35:34Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1456.5400400197243, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.72984163252576, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 19 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 49, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 49, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:36:28Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1451.714886192373, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.618761053818325, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 3, "attempted_matches": 132, "capped_draws": 108, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 66, "draws": 108, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T10:53:40Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 132, "rating_method": "sequential_elo", "raw_elo": 1457.0274966044346, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.138347031709905, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 3, "attempted_matches": 174, "capped_draws": 111, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 87, "draws": 111, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 41, "max_score": null, "measured_at": "2026-07-27T10:38:09Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 174, "rating_method": "sequential_elo", "raw_elo": 1445.4053682602037, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.50563948445921, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 21.363171103370707, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 45, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:30:17Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1443.826362619811, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.396699029090957, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 6 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 49, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 49, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:44:47Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1439.8208523917242, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.25028757645839, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 8 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 29, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 54, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:52:47Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1459.010175716237, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.1568688384384, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 41.18336395796551, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 29, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 56, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T11:36:31Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1462.1361809829436, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.02024765518864, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 46.19324853318743, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 24, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:30:10Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1458.736541116889, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.493587534338452, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 46.19324853318743, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 72, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-26T01:24:44Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1448.22814141271, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.335060663959837, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 2, "attempted_matches": 88, "capped_draws": 79, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 44, "draws": 79, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:53:34Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 88, "rating_method": "sequential_elo", "raw_elo": 1444.349744639428, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.174354772215807, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 42, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 42, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:30:14Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1436.2781128307956, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.953684555336736, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 27, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 58, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T10:51:37Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1450.4049907718822, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.71921399965224, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 42.0271267253503, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 2, "attempted_matches": 70, "capped_draws": 55, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 55, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T09:04:41Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1429.1142665897733, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.697480906486177, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3 }, { "admitted_plugins": 2, "attempted_matches": 66, "capped_draws": 38, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 33, "draws": 66, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 40, "max_score": null, "measured_at": "2026-07-27T11:52:44Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1432.644289501747, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.529651992284748, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 45.56239790693811, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 2, "attempted_matches": 138, "capped_draws": 89, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 69, "draws": 89, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 36, "max_score": null, "measured_at": "2026-07-27T10:59:44Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 138, "rating_method": "sequential_elo", "raw_elo": 1406.71166848003, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.174040290361702, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 16.016004726288628, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 57, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 57, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T11:44:31Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1402.0511352404135, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.05198164014908, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 24, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 51, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T11:52:47Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1413.5850826874466, "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": "other", "provider_model": "cohere/north-mini-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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 19.858838132294075, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 8, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 12, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T10:46:52Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1313.972577700416, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "enabled" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 3.452798895447958, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/balanced", "track_name": "Balanced filter", "uncertainty": 51.15132550669373, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 13, "attempted_matches": 662, "capped_draws": 44, "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": 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": 61.77904448694649, "contributing_entrants": null, "distinct_rated_opponents": 331, "draws": 153, "entry_count": 13, "failed_game_aliases": [ "GB2-06", "GB2-07", "GB2-08" ], "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:48:28Z", "losses": 166, "max_score": 82.43652527134509, "measured_at": null, "min_score": 48.05298165377025, "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 662, "rating_method": "sequential_elo", "raw_elo": 1657.548139470911, "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" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 58.65391822625071, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 343 }, { "admitted_plugins": 8, "attempted_matches": 504, "capped_draws": 53, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 10 }, "evidence_basis": "Standard list-price estimate", "max": 0.1598575, "mean": 0.093565, "median": 0.07461, "min": 0.06826499999999999, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 10 }, "run_count": 8, "token_priced_attempt_count": 10, "total": 0.7485199999999999 }, "codegen_evaluated_cells": 8, "conditional_success_score": 52.68516521787668, "contributing_entrants": null, "distinct_rated_opponents": 252, "draws": 195, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:23Z", "losses": 104, "max_score": 90.56767341997636, "measured_at": null, "min_score": 29.70399047704974, "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 504, "rating_method": "sequential_elo", "raw_elo": 1573.98087527373, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 52.68516521787668, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 205 }, { "admitted_plugins": 16, "attempted_matches": 570, "capped_draws": 42, "codegen_cost_usd": { "admitted_cell_count": 16, "cell_count": 8, "cost_basis_counts": { "provider_reported": 17 }, "evidence_basis": "Provider-reported", "max": 0.0820533, "mean": 0.0699502125, "median": 0.06609614999999999, "min": 0.0587988, "recorded_attempt_count": 17, "run_count": 16, "total": 1.1192034 }, "codegen_evaluated_cells": 16, "conditional_success_score": 48.725624144182824, "contributing_entrants": null, "distinct_rated_opponents": 285, "draws": 286, "entry_count": 27, "failed_game_aliases": [], "first_pass_admitted": 15, "first_pass_rate": 0.9375, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": 243, "max_score": 65.37732935727273, "measured_at": null, "min_score": 26.098699501503095, "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": 570, "rating_method": "sequential_elo", "raw_elo": 1562.656448549823, "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": 1, "repaired_rate": 0.0625, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 48.725624144182824, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 403 }, { "admitted_plugins": 8, "attempted_matches": 468, "capped_draws": 52, "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-2026-07-25": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 0.97393 }, "codegen_evaluated_cells": 8, "conditional_success_score": 46.10653397009744, "contributing_entrants": null, "distinct_rated_opponents": 234, "draws": 163, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": 141, "max_score": 57.75514722037097, "measured_at": null, "min_score": 35.54624651592337, "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": 468, "rating_method": "sequential_elo", "raw_elo": 1515.5555083722368, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 46.10653397009744, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 164 }, { "admitted_plugins": 16, "attempted_matches": 578, "capped_draws": 37, "codegen_cost_usd": { "admitted_cell_count": 16, "cell_count": 8, "cost_basis_counts": { "provider_reported": 28 }, "evidence_basis": "Provider-reported", "max": 0.116343, "mean": 0.07787519999999999, "median": 0.0843883, "min": 0.041110400000000005, "recorded_attempt_count": 28, "run_count": 16, "total": 1.2460032 }, "codegen_evaluated_cells": 16, "conditional_success_score": 45.1145758243171, "contributing_entrants": null, "distinct_rated_opponents": 289, "draws": 308, "entry_count": 28, "failed_game_aliases": [], "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:44:21Z", "losses": 255, "max_score": 74.68590448880083, "measured_at": null, "min_score": 19.6056169247618, "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 578, "rating_method": "sequential_elo", "raw_elo": 1555.2018958252147, "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" }, "repaired_admitted": 11, "repaired_rate": 0.6875, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 45.1145758243171, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 369 }, { "admitted_plugins": 8, "attempted_matches": 488, "capped_draws": 27, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 9 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 1, "max": 0.147405, "mean": 0.121464375, "median": 0.124865, "min": 0.09045, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 9 }, "run_count": 9, "token_priced_attempt_count": 9, "total": 1.069485 }, "codegen_evaluated_cells": 9, "conditional_success_score": 46.415421721995585, "contributing_entrants": null, "distinct_rated_opponents": 244, "draws": 132, "entry_count": 8, "failed_game_aliases": [ "GB2-04" ], "first_pass_admitted": 8, "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 }, "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": "2026-07-27T11:59:44Z", "losses": 171, "max_score": 57.49104851229338, "measured_at": null, "min_score": 31.688519104226355, "model_code_failure_rate": 0.1111111111111111, "model_code_failures": 1, "model_display_name": "GPT-5.6 Sol", "model_slug": "gpt-5-6-sol", "plugin_success_rate": 0.8888888888888888, "provider": "OpenAI", "provider_key": "openai", "rank": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 488, "rating_method": "sequential_elo", "raw_elo": 1516.3012269685896, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 45.06861065270844, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 185 }, { "admitted_plugins": 7, "attempted_matches": 400, "capped_draws": 14, "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-2026-07-25": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 1.262825 }, "codegen_evaluated_cells": 8, "conditional_success_score": 46.142255589163746, "contributing_entrants": null, "distinct_rated_opponents": 200, "draws": 95, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:54:26Z", "losses": 134, "max_score": 59.81731792757247, "measured_at": null, "min_score": 28.009047114593564, "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 400, "rating_method": "sequential_elo", "raw_elo": 1527.4487367440902, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 44.62732274970943, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 171 }, { "admitted_plugins": 12, "attempted_matches": 768, "capped_draws": 150, "codegen_cost_usd": { "admitted_cell_count": 12, "cell_count": 8, "cost_basis_counts": { "provider_reported": 23 }, "evidence_basis": "Provider-reported", "failed_cell_count": 2, "max": 0.00407402, "mean": 0.00223773125, "median": 0.00220356, "min": 0.00093502, "recorded_attempt_count": 23, "run_count": 14, "total": 0.03065926 }, "codegen_evaluated_cells": 14, "conditional_success_score": 45.77503697260136, "contributing_entrants": null, "distinct_rated_opponents": 384, "draws": 249, "entry_count": 12, "failed_game_aliases": [ "GB2-02", "GB2-04" ], "first_pass_admitted": 6, "first_pass_rate": 0.42857142857142855, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [ "GB2-04", "GB2-06" ], "infra_failures_excluded": 2, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:55:02Z", "losses": 265, "max_score": 58.36812405939523, "measured_at": null, "min_score": 23.723344738770017, "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 768, "rating_method": "sequential_elo", "raw_elo": 1483.2342243122505, "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" }, "repaired_admitted": 6, "repaired_rate": 0.42857142857142855, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 44.04453267378009, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 416, "capped_draws": 67, "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": 0.0216425, "min": 0.015285, "recorded_attempt_count": 9, "run_count": 8, "total": 0.18239875 }, "codegen_evaluated_cells": 8, "conditional_success_score": 45.267658771883625, "contributing_entrants": null, "distinct_rated_opponents": 208, "draws": 149, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:32Z", "losses": 136, "max_score": 78.20945134532496, "measured_at": null, "min_score": 30.15214880984472, "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": 416, "rating_method": "sequential_elo", "raw_elo": 1512.8649532761392, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 43.78144051135187, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 131 }, { "admitted_plugins": 8, "attempted_matches": 496, "capped_draws": 81, "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-2026-07-25": 10 }, "run_count": 9, "token_priced_attempt_count": 10, "total": 0.6063375 }, "codegen_evaluated_cells": 9, "conditional_success_score": 43.59133189692441, "contributing_entrants": null, "distinct_rated_opponents": 247, "draws": 221, "entry_count": 8, "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 }, "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": "2026-07-27T11:59:44Z", "losses": 149, "max_score": 56.16041187613398, "measured_at": null, "min_score": 28.668609009228703, "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": 496, "rating_method": "sequential_elo", "raw_elo": 1494.723063280869, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 1, "repaired_rate": 0.1111111111111111, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 42.326465907439584, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 126 }, { "admitted_plugins": 17, "attempted_matches": 1006, "capped_draws": 150, "codegen_cost_usd": { "admitted_cell_count": 17, "cell_count": 8, "cost_basis_counts": { "provider_reported": 35 }, "evidence_basis": "Provider-reported", "failed_cell_count": 7, "max": 0.004834030033333333, "mean": 0.0027724950333333333, "median": 0.002243999216666667, "min": 0.0016912200000000002, "recorded_attempt_count": 35, "run_count": 24, "total": 0.0665398808 }, "codegen_evaluated_cells": 24, "conditional_success_score": 44.944277213825984, "contributing_entrants": null, "distinct_rated_opponents": 503, "draws": 312, "entry_count": 17, "failed_game_aliases": [ "GB2-02", "GB2-03", "GB2-04", "GB2-07", "GB2-08" ], "first_pass_admitted": 12, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:54:00Z", "losses": 372, "max_score": 47.554841215429576, "measured_at": null, "min_score": 39.84236148945967, "model_code_failure_rate": 0.2916666666666667, "model_code_failures": 7, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": 0.7083333333333334, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1006, "rating_method": "sequential_elo", "raw_elo": 1465.3963149523474, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 5, "repaired_rate": 0.20833333333333337, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 41.23194486637451, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 322 }, { "admitted_plugins": 7, "attempted_matches": 412, "capped_draws": 97, "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-2026-07-25": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 1.13802 }, "codegen_evaluated_cells": 8, "conditional_success_score": 41.835071106564946, "contributing_entrants": null, "distinct_rated_opponents": 206, "draws": 222, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:24:42Z", "losses": 92, "max_score": 54.40691412278813, "measured_at": null, "min_score": 27.82065391961682, "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 412, "rating_method": "sequential_elo", "raw_elo": 1500.5570908453833, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 40.461550842958125, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 98 }, { "admitted_plugins": 6, "attempted_matches": 374, "capped_draws": 28, "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": 40.96023532559226, "contributing_entrants": null, "distinct_rated_opponents": 187, "draws": 108, "entry_count": 6, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:36:23Z", "losses": 142, "max_score": 65.31899895038302, "measured_at": null, "min_score": 26.62036218416104, "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 374, "rating_method": "sequential_elo", "raw_elo": 1466.500794270336, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.2857142857142857, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 39.41175239691446, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 124 }, { "admitted_plugins": 15, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 15, "cell_count": 8, "cost_basis_counts": { "provider_reported": 23 }, "evidence_basis": "Provider-reported", "failed_cell_count": 1, "max": 0.0148808, "mean": 0.0114004875, "median": 0.01124825, "min": 0.00845595, "recorded_attempt_count": 23, "run_count": 16, "total": 0.1824078 }, "codegen_evaluated_cells": 16, "conditional_success_score": 39.84087462021133, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": 228, "entry_count": 15, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-26T05:18:59Z", "losses": 202, "max_score": 66.08096329718745, "measured_at": null, "min_score": 13.059186845663168, "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": 0, "rating_method": "sequential_elo", "raw_elo": 1497.7232311729522, "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" }, "repaired_admitted": 6, "repaired_rate": 0.375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 39.203214873378464, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 189 }, { "admitted_plugins": 16, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 16, "cell_count": 8, "cost_basis_counts": { "provider_reported": 20 }, "evidence_basis": "Provider-reported", "max": 0.058529250000000005, "mean": 0.03888066562499999, "median": 0.038104875, "min": 0.029012250000000003, "recorded_attempt_count": 20, "run_count": 16, "total": 0.62209065 }, "codegen_evaluated_cells": 16, "conditional_success_score": 38.61863644188435, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": 272, "entry_count": 16, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-26T05:19:02Z", "losses": 208, "max_score": 59.08661445196189, "measured_at": null, "min_score": 24.212894203087245, "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1481.401179542269, "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" }, "repaired_admitted": 4, "repaired_rate": 0.25, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 38.61863644188435, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 180 }, { "admitted_plugins": 7, "attempted_matches": 430, "capped_draws": 84, "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": 0.015562441375, "median": 0.0131167185, "min": 0.005612805, "recorded_attempt_count": 12, "run_count": 8, "total": 0.124499531 }, "codegen_evaluated_cells": 8, "conditional_success_score": 39.69653399014509, "contributing_entrants": null, "distinct_rated_opponents": 214, "draws": 152, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": 141, "max_score": 74.39181497022835, "measured_at": null, "min_score": 21.132140682151817, "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 430, "rating_method": "sequential_elo", "raw_elo": 1471.0109295011357, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 38.39322572776556, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 6, "attempted_matches": 372, "capped_draws": 22, "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": 40.77789385607518, "contributing_entrants": null, "distinct_rated_opponents": 186, "draws": 97, "entry_count": 6, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:30:08Z", "losses": 135, "max_score": 52.69666989897096, "measured_at": null, "min_score": 27.899111953447644, "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 372, "rating_method": "sequential_elo", "raw_elo": 1484.0635842495656, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 37.94810616641322, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 140 }, { "admitted_plugins": 8, "attempted_matches": 276, "capped_draws": 22, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 13 }, "evidence_basis": "Standard list-price estimate", "max": 0.136952, "mean": 0.07424775, "median": 0.070604, "min": 0.041758, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 13 }, "run_count": 8, "token_priced_attempt_count": 13, "total": 0.593982 }, "codegen_evaluated_cells": 8, "conditional_success_score": 36.72182476113313, "contributing_entrants": null, "distinct_rated_opponents": 137, "draws": 87, "entry_count": 12, "failed_game_aliases": [], "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": 92, "max_score": 83.5076304126712, "measured_at": null, "min_score": 17.83316943117343, "model_code_failure_rate": 0.0, "model_code_failures": 0, "model_display_name": "O3", "model_slug": "o3", "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": 276, "rating_method": "sequential_elo", "raw_elo": 1515.2721863391596, "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": 4, "repaired_rate": 0.5, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 36.72182476113313, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 111 }, { "admitted_plugins": 6, "attempted_matches": 404, "capped_draws": 80, "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": 38.897398778071, "contributing_entrants": null, "distinct_rated_opponents": 202, "draws": 193, "entry_count": 6, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:48:11Z", "losses": 108, "max_score": 71.25680984831166, "measured_at": null, "min_score": 26.336139967911993, "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 404, "rating_method": "sequential_elo", "raw_elo": 1487.264677108794, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 36.19810830930494, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 103 }, { "admitted_plugins": 7, "attempted_matches": 274, "capped_draws": 47, "codegen_cost_usd": { "admitted_cell_count": 7, "cell_count": 8, "cost_basis_counts": { "provider_reported": 20 }, "evidence_basis": "Provider-reported", "failed_cell_count": 1, "max": 0.03772852, "mean": 0.024905897500000003, "median": 0.0260953, "min": 0.00984735, "recorded_attempt_count": 20, "run_count": 8, "total": 0.19924718 }, "codegen_evaluated_cells": 8, "conditional_success_score": 37.07527376145696, "contributing_entrants": null, "distinct_rated_opponents": 137, "draws": 75, "entry_count": 7, "failed_game_aliases": [ "GB2-02" ], "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:44:14Z", "losses": 112, "max_score": 48.91915370704513, "measured_at": null, "min_score": 19.24313559757037, "model_code_failure_rate": 0.125, "model_code_failures": 1, "model_display_name": "Step 3.7 Flash", "model_slug": "stepfun-step-3-7-flash", "plugin_success_rate": 0.875, "provider": "StepFun", "provider_key": "stepfun", "rank": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 274, "rating_method": "sequential_elo", "raw_elo": 1457.3245219395228, "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" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 35.858026164090255, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 87 }, { "admitted_plugins": 14, "attempted_matches": 892, "capped_draws": 158, "codegen_cost_usd": { "admitted_cell_count": 14, "cell_count": 8, "cost_basis_counts": { "provider_reported": 25 }, "evidence_basis": "Provider-reported", "failed_cell_count": 2, "max": 0.014209038, "mean": 0.0093957345, "median": 0.009312405, "min": 0.004429524000000001, "recorded_attempt_count": 25, "run_count": 16, "total": 0.150331752 }, "codegen_evaluated_cells": 16, "conditional_success_score": 36.52896680779845, "contributing_entrants": null, "distinct_rated_opponents": 446, "draws": 307, "entry_count": 14, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:54:00Z", "losses": 338, "max_score": 52.38713921457689, "measured_at": null, "min_score": 21.811735212142757, "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 892, "rating_method": "sequential_elo", "raw_elo": 1452.8076610451176, "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" }, "repaired_admitted": 6, "repaired_rate": 0.375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 35.32965544553668, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 247 }, { "admitted_plugins": 12, "attempted_matches": 736, "capped_draws": 70, "codegen_cost_usd": { "admitted_cell_count": 12, "cell_count": 8, "cost_basis_counts": { "provider_reported": 28 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.053540475, "mean": 0.026315053125, "median": 0.024512850000000003, "min": 0.012912625, "recorded_attempt_count": 28, "run_count": 16, "total": 0.42104085 }, "codegen_evaluated_cells": 16, "conditional_success_score": 36.551991647127046, "contributing_entrants": null, "distinct_rated_opponents": 368, "draws": 247, "entry_count": 12, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:37:44Z", "losses": 303, "max_score": 49.94247004323288, "measured_at": null, "min_score": 26.11987489541008, "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 736, "rating_method": "sequential_elo", "raw_elo": 1461.4945458521415, "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" }, "repaired_admitted": 5, "repaired_rate": 0.3125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 34.01546103667579, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 186 }, { "admitted_plugins": 24, "attempted_matches": 1432, "capped_draws": 196, "codegen_cost_usd": { "admitted_cell_count": 24, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 29 }, "evidence_basis": "Standard list-price estimate", "max": 0.021615250000000003, "mean": 0.017288937500000004, "median": 0.01830825, "min": 0.01259225, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 29 }, "run_count": 24, "token_priced_attempt_count": 29, "total": 0.4149345 }, "codegen_evaluated_cells": 24, "conditional_success_score": 33.58863538792332, "contributing_entrants": null, "distinct_rated_opponents": 715, "draws": 588, "entry_count": 24, "failed_game_aliases": [], "first_pass_admitted": 19, "first_pass_rate": 0.7916666666666666, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": 496, "max_score": 49.45153806809078, "measured_at": null, "min_score": 21.382657975617843, "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1432, "rating_method": "sequential_elo", "raw_elo": 1427.5369329615808, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 5, "repaired_rate": 0.20833333333333337, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 33.58863538792332, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 348 }, { "admitted_plugins": 8, "attempted_matches": 288, "capped_draws": 41, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "provider_reported": 13 }, "evidence_basis": "Provider-reported", "max": 0.0032939400000000004, "mean": 0.0016413085, "median": 0.0014119655, "min": 0.00045831, "recorded_attempt_count": 13, "run_count": 8, "total": 0.013130468 }, "codegen_evaluated_cells": 8, "conditional_success_score": 31.740856996211672, "contributing_entrants": null, "distinct_rated_opponents": 144, "draws": 113, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:32Z", "losses": 106, "max_score": 47.15146009630666, "measured_at": null, "min_score": 14.420068188974202, "model_code_failure_rate": 0.0, "model_code_failures": 0, "model_display_name": "GPT-OSS 120B", "model_slug": "openai-gpt-oss-120b", "plugin_success_rate": 1.0, "provider": "OpenAI", "provider_key": "openai", "rank": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 288, "rating_method": "sequential_elo", "raw_elo": 1438.9374320645486, "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" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 31.740856996211672, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 69 }, { "admitted_plugins": 6, "attempted_matches": 334, "capped_draws": 59, "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": 32.157004896285834, "contributing_entrants": null, "distinct_rated_opponents": 167, "draws": 100, "entry_count": 6, "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 }, "infra_excluded_game_aliases": [ "GB2-02" ], "infra_failures_excluded": 1, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:24:44Z", "losses": 137, "max_score": 44.68186759149837, "measured_at": null, "min_score": 21.93738491295836, "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 334, "rating_method": "sequential_elo", "raw_elo": 1410.5889455812448, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 1, "repaired_rate": 0.14285714285714285, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 30.941324060385092, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 97 }, { "admitted_plugins": 19, "attempted_matches": 1138, "capped_draws": 180, "codegen_cost_usd": { "admitted_cell_count": 19, "cell_count": 8, "cost_basis_counts": { "provider_reported": 34 }, "evidence_basis": "Provider-reported", "failed_cell_count": 5, "max": 0.0027823742, "mean": 0.0022230800541666665, "median": 0.002112839, "min": 0.001825724, "recorded_attempt_count": 34, "run_count": 24, "total": 0.0533539213 }, "codegen_evaluated_cells": 24, "conditional_success_score": 32.397303698325416, "contributing_entrants": null, "distinct_rated_opponents": 569, "draws": 471, "entry_count": 19, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-06" ], "first_pass_admitted": 14, "first_pass_rate": 0.5833333333333334, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": 407, "max_score": 38.6894460221831, "measured_at": null, "min_score": 26.61960427875735, "model_code_failure_rate": 0.20833333333333337, "model_code_failures": 5, "model_display_name": "DeepSeek V4 Flash", "model_slug": "deepseek-deepseek-v4-flash", "plugin_success_rate": 0.7916666666666666, "provider": "DeepSeek", "provider_key": "deepseek", "rank": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1138, "rating_method": "sequential_elo", "raw_elo": 1436.513869453124, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 5, "repaired_rate": 0.20833333333333337, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 30.559374230943043, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 260 }, { "admitted_plugins": 25, "attempted_matches": 1504, "capped_draws": 249, "codegen_cost_usd": { "admitted_cell_count": 25, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 56 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 7, "max": 0.013223525, "mean": 0.0089983359375, "median": 0.00845865, "min": 0.0058062875, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 56 }, "run_count": 32, "token_priced_attempt_count": 56, "total": 0.28794675000000003 }, "codegen_evaluated_cells": 32, "conditional_success_score": 32.37514569421184, "contributing_entrants": null, "distinct_rated_opponents": 752, "draws": 593, "entry_count": 25, "failed_game_aliases": [ "GB2-03", "GB2-04", "GB2-05", "GB2-06", "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": 536, "max_score": 36.489269004581146, "measured_at": null, "min_score": 28.309344060133164, "model_code_failure_rate": 0.21875, "model_code_failures": 7, "model_display_name": "GPT-5.4 Nano", "model_slug": "gpt-5-4-nano", "plugin_success_rate": 0.78125, "provider": "OpenAI", "provider_key": "openai", "rank": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1504, "rating_method": "sequential_elo", "raw_elo": 1446.818247883918, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 15, "repaired_rate": 0.46875, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 30.43751825919392, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 375 }, { "admitted_plugins": 6, "attempted_matches": 344, "capped_draws": 18, "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": 30.53831550280331, "contributing_entrants": null, "distinct_rated_opponents": 172, "draws": 100, "entry_count": 6, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:44:24Z", "losses": 152, "max_score": 35.74840773334668, "measured_at": null, "min_score": 18.05367245403799, "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 344, "rating_method": "sequential_elo", "raw_elo": 1402.985140004401, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.2222222222222222, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 27.594483075202657, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 92 }, { "admitted_plugins": 10, "attempted_matches": 604, "capped_draws": 147, "codegen_cost_usd": { "admitted_cell_count": 10, "cell_count": 8, "cost_basis_counts": { "provider_reported": 29 }, "evidence_basis": "Provider-reported", "failed_cell_count": 6, "max": 0.0, "mean": 0.0, "median": 0.0, "min": 0.0, "recorded_attempt_count": 29, "run_count": 16, "total": 0.0 }, "codegen_evaluated_cells": 16, "conditional_success_score": 28.79431096575087, "contributing_entrants": null, "distinct_rated_opponents": 302, "draws": 302, "entry_count": 10, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:48:36Z", "losses": 215, "max_score": 44.131890322774105, "measured_at": null, "min_score": 18.594475422927697, "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 604, "rating_method": "sequential_elo", "raw_elo": 1414.0503243261192, "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": 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" }, "repaired_admitted": 4, "repaired_rate": 0.25, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 25.602165158326375, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 87 }, { "admitted_plugins": 8, "attempted_matches": 454, "capped_draws": 66, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 9 }, "evidence_basis": "Standard list-price estimate", "max": 0.038815, "mean": 0.02196775, "median": 0.0196975, "min": 0.016152, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 0.17574199999999998 }, "codegen_evaluated_cells": 8, "conditional_success_score": 23.750537922707625, "contributing_entrants": null, "distinct_rated_opponents": 227, "draws": 185, "entry_count": 8, "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 }, "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": "2026-07-27T11:59:32Z", "losses": 206, "max_score": 42.8401440385904, "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": 453, "rating_method": "sequential_elo", "raw_elo": 1352.506391499512, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 23.750537922707625, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 62 }, { "admitted_plugins": 8, "attempted_matches": 328, "capped_draws": 58, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 164, "draws": 132, "entry_count": 8, "failed_game_aliases": [], "first_pass_admitted": null, "first_pass_rate": null, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:54:22Z", "losses": 98, "max_score": 55.05572388516481, "measured_at": null, "min_score": 26.09668923633087, "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": "provisional", "rated_matches": 328, "rating_method": "sequential_elo", "raw_elo": 1501.062269125725, "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": "omitted", "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": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 41.45827687268098, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 98 }, { "admitted_plugins": 28, "attempted_matches": 1140, "capped_draws": 73, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 570, "draws": 328, "entry_count": 28, "failed_game_aliases": [], "first_pass_admitted": null, "first_pass_rate": null, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:55:02Z", "losses": 420, "max_score": 53.48050971680028, "measured_at": null, "min_score": 26.49126905850573, "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": "provisional", "rated_matches": 1140, "rating_method": "sequential_elo", "raw_elo": 1488.6998716279136, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 39.66616940391225, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 392 }, { "admitted_plugins": 8, "attempted_matches": 332, "capped_draws": 28, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 165, "draws": 100, "entry_count": 8, "failed_game_aliases": [], "first_pass_admitted": null, "first_pass_rate": null, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:48:31Z", "losses": 128, "max_score": 56.67090350467359, "measured_at": null, "min_score": 22.47989431367969, "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": "provisional", "rated_matches": 332, "rating_method": "sequential_elo", "raw_elo": 1473.9505577611824, "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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 37.36024586658148, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 104 }, { "admitted_plugins": 7, "attempted_matches": 404, "capped_draws": 50, "codegen_cost_usd": { "admitted_cell_count": 7, "cell_count": 8, "cost_basis_counts": { "provider_reported": 33 }, "evidence_basis": "Provider-reported", "failed_cell_count": 9, "max": 0.2156775, "mean": 0.157461515625, "median": 0.15705206249999998, "min": 0.098579625, "recorded_attempt_count": 33, "run_count": 16, "total": 2.51938425 }, "codegen_evaluated_cells": 16, "conditional_success_score": 45.44597930886597, "contributing_entrants": null, "distinct_rated_opponents": 201, "draws": 168, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:59:44Z", "losses": 130, "max_score": 68.47656737578293, "measured_at": null, "min_score": 25.16068625041128, "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": 404, "rating_method": "sequential_elo", "raw_elo": 1468.4155253243164, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 7, "repaired_rate": 0.4375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 36.96068238360196, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 106 }, { "admitted_plugins": 7, "attempted_matches": 288, "capped_draws": 53, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 144, "draws": 94, "entry_count": 7, "failed_game_aliases": [], "first_pass_admitted": null, "first_pass_rate": null, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:54:18Z", "losses": 112, "max_score": 53.32304855651662, "measured_at": null, "min_score": 20.745733263714285, "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": "provisional", "rated_matches": 288, "rating_method": "sequential_elo", "raw_elo": 1447.0488191118857, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 35.241132026567165, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 82 }, { "admitted_plugins": 4, "attempted_matches": 252, "capped_draws": 53, "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": 0.0429946875, "median": 0.0423105, "min": 0.0223935, "recorded_attempt_count": 14, "run_count": 8, "total": 0.34395749999999997 }, "codegen_evaluated_cells": 8, "conditional_success_score": 32.10501667536629, "contributing_entrants": null, "distinct_rated_opponents": 125, "draws": 58, "entry_count": 4, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:52:31Z", "losses": 113, "max_score": 38.70088877553203, "measured_at": null, "min_score": 25.961097857676517, "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": 249, "rating_method": "sequential_elo", "raw_elo": 1401.2485940757429, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 26.996993433976236, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 3, "wins": 78 }, { "admitted_plugins": 5, "attempted_matches": 212, "capped_draws": 23, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 106, "draws": 58, "entry_count": 5, "failed_game_aliases": [], "first_pass_admitted": null, "first_pass_rate": null, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:18:10Z", "losses": 107, "max_score": 40.02316688669191, "measured_at": null, "min_score": 0.0, "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": "provisional", "rated_matches": 212, "rating_method": "sequential_elo", "raw_elo": 1340.8690817061367, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 23.388684213793677, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": null, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugins": 5, "attempted_matches": 324, "capped_draws": 110, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 29 }, "evidence_basis": "Provider-reported", "failed_cell_count": 11, "max": 0.0, "mean": 0.0, "median": 0.0, "min": 0.0, "recorded_attempt_count": 29, "run_count": 16, "total": 0.0 }, "codegen_evaluated_cells": 16, "conditional_success_score": 27.36940382474815, "contributing_entrants": null, "distinct_rated_opponents": 160, "draws": 110, "entry_count": 5, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:36:23Z", "losses": 154, "max_score": 27.58246377184411, "measured_at": null, "min_score": 27.1563438776522, "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": 324, "rating_method": "sequential_elo", "raw_elo": 1377.562628113915, "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": "other", "provider_model": "cohere/north-mini-code", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 20.46340232604428, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1, "attempted_matches": 62, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T11:24:40Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1828.996677787992, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 90.56767341997636, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 54 }, { "admitted_plugins": 1, "attempted_matches": 72, "capped_draws": 15, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 36, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:20:39Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 72, "rating_method": "sequential_elo", "raw_elo": 1676.59501851212, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 71.25680984831166, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 42 }, { "admitted_plugins": 2, "attempted_matches": 100, "capped_draws": 44, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 50, "draws": 44, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T10:36:06Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 100, "rating_method": "sequential_elo", "raw_elo": 1663.2578169032925, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 68.33312358571251, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 17, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 17, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T11:16:48Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1582.8274794165334, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 58.72679193774028, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 29 }, { "admitted_plugins": 2, "attempted_matches": 134, "capped_draws": 29, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 67, "draws": 29, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 53, "max_score": null, "measured_at": "2026-07-27T11:55:02Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 134, "rating_method": "sequential_elo", "raw_elo": 1578.9605026224492, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 58.36812405939523, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 16.888824360518605, "unilateral_faults": 0, "wins": 52 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 14, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 14, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-27T11:08:58Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1577.025901566621, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.41317066463946, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T11:48:31Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1576.9979684590764, "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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 56.67090350467359, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 18, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 18, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:16:35Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1564.6500398829733, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 56.16041187613398, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 18 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 15, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:20:42Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1563.2313436316006, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 56.082660301584646, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 2, "attempted_matches": 76, "capped_draws": 35, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 38, "draws": 65, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-27T11:16:11Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1575.662991828095, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.99220669211011, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 35.655011583130054, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 12, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 12, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:23:03Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1562.54730392307, "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": "omitted", "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": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 54.79582315352283, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 2, "attempted_matches": 76, "capped_draws": 29, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 38, "draws": 65, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:09:22Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1563.4119554419992, "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 54.4025443238804, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 35.655011583130054, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 11, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-27T11:54:18Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1551.1970854508706, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.32304855651662, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 20, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 35, "max_score": null, "measured_at": "2026-07-26T05:08:25Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1511.9250538429842, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.95394531902585, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 33.41808305530269, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 15, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T10:25:02Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1497.3874694861893, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.91834193923778, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32 }, { "admitted_plugins": 1, "attempted_matches": 74, "capped_draws": 27, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 37, "draws": 27, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:31:26Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1494.5716412258355, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.71947792576954, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 23 }, { "admitted_plugins": 3, "attempted_matches": 204, "capped_draws": 51, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 102, "draws": 51, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 82, "max_score": null, "measured_at": "2026-07-27T11:54:00Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 204, "rating_method": "sequential_elo", "raw_elo": 1495.360690744961, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.554841215429576, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 16.557344098906125, "unilateral_faults": 0, "wins": 71 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 50, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:24:42Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1489.9225771870858, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 46.76850942142567, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 2, "attempted_matches": 132, "capped_draws": 41, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 66, "draws": 41, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 48, "max_score": null, "measured_at": "2026-07-27T11:54:00Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 132, "rating_method": "sequential_elo", "raw_elo": 1480.535597443261, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.54198211998018, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.416580872281934, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 23, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 23, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:05:07Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1480.1694379737794, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.502967642683174, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 13, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 13, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:24:40Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1479.5735802409645, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.89189158155693, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 18 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 16, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 16, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-27T10:37:13Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1477.0492603937407, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.68186759149837, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 25 }, { "admitted_plugins": 2, "attempted_matches": 124, "capped_draws": 35, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 62, "draws": 35, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 53, "max_score": null, "measured_at": "2026-07-27T11:48:36Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 124, "rating_method": "sequential_elo", "raw_elo": 1471.1495141356838, "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": 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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.131890322774105, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 36 }, { "admitted_plugins": 4, "attempted_matches": 176, "capped_draws": 23, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 88, "draws": 23, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 80, "max_score": null, "measured_at": "2026-07-27T11:54:18Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1479.3211820076922, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.99088017788524, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 30.8408904576248, "unilateral_faults": 0, "wins": 73 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:05:07Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1483.123014784552, "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.91604697226371, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 38, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T11:07:18Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1445.0343615965558, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.41017310675189, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 10 }, { "admitted_plugins": 1, "attempted_matches": 76, "capped_draws": 24, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 38, "draws": 24, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:26:17Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1431.6560101881555, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.63405689209577, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 23 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 30, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-26T02:18:45Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1427.0613921129166, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.84688237866748, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 19 }, { "admitted_plugins": 4, "attempted_matches": 260, "capped_draws": 76, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 130, "draws": 76, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 117, "max_score": null, "measured_at": "2026-07-27T11:37:35Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 260, "rating_method": "sequential_elo", "raw_elo": 1411.2303820418765, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.489269004581146, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.99313799115447, "unilateral_faults": 0, "wins": 67 }, { "admitted_plugins": 3, "attempted_matches": 196, "capped_draws": 65, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 98, "draws": 65, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 86, "max_score": null, "measured_at": "2026-07-27T11:20:42Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 196, "rating_method": "sequential_elo", "raw_elo": 1405.0885978520623, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.72273833543881, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.700176346389366, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 11, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:09:22Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1413.0817228894214, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.827672532836864, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 6, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T11:16:08Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 61, "rating_method": "sequential_elo", "raw_elo": 1393.6204375879504, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.02186953365919, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 19.750063500095248, "unilateral_faults": 3, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 18, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 18, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:07:18Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1378.486150271109, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.3088107693705, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 16, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 16, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:08:57Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 59, "rating_method": "sequential_elo", "raw_elo": 1357.846690093915, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.271001037603703, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 20.79972243679028, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 2, "attempted_matches": 132, "capped_draws": 61, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 66, "draws": 61, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 55, "max_score": null, "measured_at": "2026-07-27T11:24:41Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 132, "rating_method": "sequential_elo", "raw_elo": 1342.0779950278898, "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": "other", "provider_model": "cohere/north-mini-code", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.58246377184411, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.355146918744417, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 2, "attempted_matches": 122, "capped_draws": 57, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 61, "draws": 57, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 50, "max_score": null, "measured_at": "2026-07-27T10:30:48Z", "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": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 122, "rating_method": "sequential_elo", "raw_elo": 1332.7271647404896, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.11987489541008, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 19.7562594006596, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 23, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 23, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-27T08:33:33Z", "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": 37, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1340.1564195017108, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.105376543268523, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 2, "attempted_matches": 100, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 50, "draws": 49, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T09:25:48Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 100, "rating_method": "sequential_elo", "raw_elo": 1614.1052407283012, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 60.19441308419789, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T09:06:59Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1507.016974397993, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.54624651592337, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 62, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T10:49:50Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1501.313222137573, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.77155592483919, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 64, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T11:10:15Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1499.1390170008954, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.43031617632999, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 42, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T10:49:51Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1501.132056255132, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.69550841012682, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 50, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 46, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T10:49:50Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1502.5488228935112, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.53817330743257, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 50, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 48, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T10:46:41Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1502.3246516528714, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.484607923588854, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 3, "attempted_matches": 170, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 85, "draws": 162, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T10:49:51Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 170, "rating_method": "sequential_elo", "raw_elo": 1498.942537588182, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.45694771758166, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 22.181059143734817, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 2, "attempted_matches": 108, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 54, "draws": 106, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T11:23:02Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 108, "rating_method": "sequential_elo", "raw_elo": 1492.4830875314651, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.570829807726735, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 23.97350569750971, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 48, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 0, "max_score": null, "measured_at": "2026-07-27T10:46:41Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1495.4141301372438, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.562942122426243, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 60, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T10:49:49Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1488.5809352786268, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.542487942751787, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 58, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 0, "max_score": null, "measured_at": "2026-07-27T10:03:08Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1488.7189255222488, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.173955008668692, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 34, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T11:18:10Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1495.250360698582, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.873056729095698, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 63, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T11:18:19Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1480.524029567731, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.80400934470667, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 56, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T10:49:51Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1479.9188889322822, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.659411891774138, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 60, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T11:26:34Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1477.653649416274, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.11813628556075, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 2 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 39, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T10:46:41Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1489.8564736994583, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.962153891671328, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 57, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T09:27:48Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1477.2364928140053, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.8317503237067, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 2 }, { "admitted_plugins": 4, "attempted_matches": 212, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 106, "draws": 195, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T11:10:15Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 212, "rating_method": "sequential_elo", "raw_elo": 1479.1796174954648, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.309344060133164, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 24.405823784913025, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 44, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T10:46:40Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1477.334204135014, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.009047114593564, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 55, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T10:49:49Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1475.919430546933, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.899111953447644, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 60, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T11:26:28Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1472.8398095919308, "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": 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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.7811694206549, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 76, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-26T01:22:00Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1480.0137295267718, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.61024484133727, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 3, "attempted_matches": 114, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 57, "draws": 103, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T11:37:26Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 114, "rating_method": "sequential_elo", "raw_elo": 1481.097572399547, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.49126905850573, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 77, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-26T02:16:39Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1479.3227937021456, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.445146755820858, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 57, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T10:49:42Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1466.7923583848676, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.336139967911993, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 53, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T10:49:51Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1468.5821896697769, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.14588918135212, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 74, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 37, "draws": 108, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T10:46:40Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1491.4134151097094, "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.098699501503095, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 51.26251078619039, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 35, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T09:04:37Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1479.446255038946, "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": "omitted", "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": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.09668923633087, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 46, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T11:48:23Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1466.422044691208, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.16068625041128, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 16, "draws": 30, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T10:49:48Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1479.8188659817515, "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.852438966409498, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 21, "draws": 31, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:48:23Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1461.1826663180202, "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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.789449128010855, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 74, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 37, "draws": 108, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T10:46:40Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1471.8149295217936, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.448445079116, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 51.09105910444126, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 60, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 30, "draws": 28, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T11:04:58Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1583.1305040657564, "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 58.36864528288711, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 40.429265925240735, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 29, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T11:02:46Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1557.0056967199416, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.46990711066279, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 10, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-26T04:32:18Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1555.427920742531, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.20287523182865, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 8, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 35, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T10:58:07Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1543.043331713756, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.68257145959784, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 20, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:18:16Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1537.2180654375327, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.69666989897096, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 32, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-26T04:27:36Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1536.9110831145465, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.49549503671918, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 33.41808305530269, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 1, "attempted_matches": 42, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 21, "draws": 19, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:58:08Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1532.8195170122888, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.9274169728892, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 28, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T10:58:00Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1525.5217643839485, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.14138536541297, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 2, "attempted_matches": 96, "capped_draws": 12, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 48, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T11:37:44Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 96, "rating_method": "sequential_elo", "raw_elo": 1523.1433202477533, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.94247004323288, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugins": 2, "attempted_matches": 82, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 41, "draws": 12, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T11:48:28Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 82, "rating_method": "sequential_elo", "raw_elo": 1527.3550606101735, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.87817883970666, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 33.41808305530269, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 3, "attempted_matches": 146, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 73, "draws": 93, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T11:03:11Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 146, "rating_method": "sequential_elo", "raw_elo": 1520.0022000607769, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.45153806809078, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 27.37805230829621, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 6, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 21, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:05:36Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1522.423633843672, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.91915370704513, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 9 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 15, "draws": 10, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:18:20Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1527.2252132901654, "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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.1455251873211, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 10, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 23, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T11:38:14Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1507.1274179692712, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.77459545300492, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 24, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 16, "max_score": null, "measured_at": "2026-07-27T11:02:50Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1492.4298015489974, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.28708633683153, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 19, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T09:13:01Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1482.3818845275205, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.8401440385904, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 13, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:30:40Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1485.0924616716402, "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": "omitted", "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": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.333305859069256, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 2, "attempted_matches": 102, "capped_draws": 8, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 51, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:54:30Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 102, "rating_method": "sequential_elo", "raw_elo": 1475.2414972738902, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.117108402114056, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 25.597143087872503, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugins": 2, "attempted_matches": 106, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 53, "draws": 44, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 34, "max_score": null, "measured_at": "2026-07-27T11:31:38Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 106, "rating_method": "sequential_elo", "raw_elo": 1472.639729959869, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.7947922039493, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 24.72546785769763, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 15, "draws": 21, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T00:11:53Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1478.271732610354, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.860356628188114, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 28, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T08:10:00Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1457.46717560364, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.62343543749571, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 3, "attempted_matches": 152, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 76, "draws": 61, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 53, "max_score": null, "measured_at": "2026-07-27T11:37:44Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 152, "rating_method": "sequential_elo", "raw_elo": 1451.0828773497008, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.956034447719695, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 26.131352980601804, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 23, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T11:48:11Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1436.7909872054654, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.848972779507136, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 50, "capped_draws": 3, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 39, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:02:50Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1441.1397761187798, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.25524629697736, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 2, "attempted_matches": 100, "capped_draws": 6, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 50, "draws": 46, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:48:11Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 100, "rating_method": "sequential_elo", "raw_elo": 1437.3954080780577, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.61605485008677, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 26.304426701457977, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 3, "attempted_matches": 88, "capped_draws": 10, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 44, "draws": 46, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T11:54:30Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 88, "rating_method": "sequential_elo", "raw_elo": 1452.8816556321274, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.413074688495364, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 47.161388718300266, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 27, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T11:05:07Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1424.386156653482, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.02461357020887, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 15, "draws": 18, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:31:27Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1419.261890549445, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.873191643532166, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 96, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 48, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 41, "max_score": null, "measured_at": "2026-07-27T08:56:36Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 96, "rating_method": "sequential_elo", "raw_elo": 1394.10982893775, "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": 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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.098050691260877, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 27.72324997517388, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugins": 1, "attempted_matches": 30, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 15, "draws": 19, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:03:09Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 30, "rating_method": "sequential_elo", "raw_elo": 1457.5588113209724, "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.89145366159343, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 73.02632550669372, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 50, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 14, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 27, "max_score": null, "measured_at": "2026-07-27T11:05:36Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1351.7838803092702, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.132140682151817, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 2, "attempted_matches": 68, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 34, "draws": 37, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 60, "max_score": null, "measured_at": "2026-07-27T11:05:06Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1352.8740700973729, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 19.6056169247618, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 38.90120295341135, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 34, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T08:41:56Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1569.103382231883, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.13435586825387, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 15 }, { "admitted_plugins": 2, "attempted_matches": 104, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 52, "draws": 37, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:51:49Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 104, "rating_method": "sequential_elo", "raw_elo": 1562.4138188466493, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.05298165377025, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 24.966995223862348, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugins": 1, "attempted_matches": 74, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 37, "draws": 69, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T10:45:27Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1520.6818659965604, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.48990096796995, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:02:36Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1529.4343084381378, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.48915163819359, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 57, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-26T05:18:59Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1526.9657349005845, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.71926929378232, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 32.95048007367414, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T10:58:02Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1517.8546980180151, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.74445802482134, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 17, "draws": 29, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T07:29:58Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1527.3928154870323, "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": "omitted", "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": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.55892538039321, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 2, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 30, "draws": 66, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T11:05:41Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1520.5747166006124, "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.23936078612753, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 40.52299760510738, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 1, "attempted_matches": 24, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 12, "draws": 13, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T09:05:32Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 24, "rating_method": "sequential_elo", "raw_elo": 1529.6913005047602, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.549112144936515, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 56.25, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 46, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T10:52:42Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1496.2226687102534, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.93505786860947, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 6 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 49, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:52:49Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1494.2473590945217, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.83231653302763, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 11 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 34, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T08:21:31Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1508.141304108455, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.74840773334668, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 42, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:05:28Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1496.0402265733064, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.57981567734945, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 7 }, { "admitted_plugins": 2, "attempted_matches": 102, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 51, "draws": 83, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T10:52:53Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 102, "rating_method": "sequential_elo", "raw_elo": 1499.5984918963782, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.42714387532118, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 25.674278837447822, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 4, "attempted_matches": 148, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 74, "draws": 103, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T10:48:24Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 148, "rating_method": "sequential_elo", "raw_elo": 1507.548288827742, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.14502822780986, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 37.38178527761111, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 2, "attempted_matches": 118, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 59, "draws": 87, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T10:58:30Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 118, "rating_method": "sequential_elo", "raw_elo": 1487.2679557249785, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.746597116010264, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 20.80644772842997, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 1, "attempted_matches": 50, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 25, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T10:52:51Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 50, "rating_method": "sequential_elo", "raw_elo": 1491.333286691229, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.686693364975824, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 41, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T11:05:41Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1490.2406649219877, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.243606728345505, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 27, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T10:48:31Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1495.9623564264125, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.00720768323213, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 55, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T10:43:48Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1477.6032838196008, "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": 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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.907085942540736, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1 }, { "admitted_plugins": 3, "attempted_matches": 180, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 90, "draws": 129, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T10:52:42Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 180, "rating_method": "sequential_elo", "raw_elo": 1477.4032418008044, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.776589675258645, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 20.8372443910451, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T08:39:01Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1480.2355614499472, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.688519104226355, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 34, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:02:41Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1481.9095702707032, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.08886348521295, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 112, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 56, "draws": 80, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T10:51:47Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 112, "rating_method": "sequential_elo", "raw_elo": 1472.803460952347, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.55482235515263, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 22.75404151813585, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 66, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-26T02:18:41Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1479.7916569609888, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.101018497465517, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 5 }, { "admitted_plugins": 3, "attempted_matches": 166, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 83, "draws": 143, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T11:05:28Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 166, "rating_method": "sequential_elo", "raw_elo": 1454.7935010604235, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.84312128528944, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 23.53231309379926, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 70, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 35, "draws": 88, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T11:04:59Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1503.7176031214149, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.895985669966077, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 54.39938126480841, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 28, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 14, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:58:30Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 28, "rating_method": "sequential_elo", "raw_elo": 1468.27005544933, "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.45352145685857, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 17, "draws": 23, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-26T22:08:31Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1458.5374385455698, "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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.842595418716364, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 22, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 11, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T10:52:47Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 22, "rating_method": "sequential_elo", "raw_elo": 1422.0102326087713, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 14.420068188974202, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 2, "attempted_matches": 114, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 57, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T11:10:13Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 114, "rating_method": "sequential_elo", "raw_elo": 1814.2964967335272, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 82.43652527134509, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 85 }, { "admitted_plugins": 1, "attempted_matches": 80, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 40, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:24:38Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1744.8030888257304, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 75.10136719944344, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 55 }, { "admitted_plugins": 2, "attempted_matches": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 38, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 40, "max_score": null, "measured_at": "2026-07-27T11:16:49Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1628.4382549178165, "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 59.03608650610162, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 34.471251018360036, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:09:34Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1587.9373567546218, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.746785917192774, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 39 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T11:07:21Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1583.9989523111312, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 54.98231754257976, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 35 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:20:59Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1578.3209032811378, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 54.40691412278813, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 35 }, { "admitted_plugins": 2, "attempted_matches": 132, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 66, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 56, "max_score": null, "measured_at": "2026-07-27T11:08:00Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 132, "rating_method": "sequential_elo", "raw_elo": 1547.7029292841976, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.0280823912595, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.355146918744417, "unilateral_faults": 0, "wins": 76 }, { "admitted_plugins": 2, "attempted_matches": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 38, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 46, "max_score": null, "measured_at": "2026-07-27T11:24:39Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1596.2341577964626, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.161802776181965, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 50.85343826377003, "unilateral_faults": 0, "wins": 76 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 16, "max_score": null, "measured_at": "2026-07-27T11:06:11Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1544.427991149785, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.650421679977455, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 40, "max_score": null, "measured_at": "2026-07-26T05:18:07Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1536.7147699474256, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.4785629543956, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 30.300442572851765, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:07:15Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1523.974286932912, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.01327090561448, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 38 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 34, "max_score": null, "measured_at": "2026-07-27T10:13:23Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1521.2856555640442, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.692122535876926, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T08:07:17Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1469.451876888559, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.85000638911461, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 33 }, { "admitted_plugins": 1, "attempted_matches": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 38, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 42, "max_score": null, "measured_at": "2026-07-27T11:21:01Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1459.739093474812, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.915245999404725, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 34 }, { "admitted_plugins": 3, "attempted_matches": 184, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 92, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 91, "max_score": null, "measured_at": "2026-07-27T11:44:21Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 184, "rating_method": "sequential_elo", "raw_elo": 1455.8411759214753, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.84236148945967, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 19.5855325453968, "unilateral_faults": 0, "wins": 93 }, { "admitted_plugins": 2, "attempted_matches": 142, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 71, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 85, "max_score": null, "measured_at": "2026-07-27T11:08:02Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 142, "rating_method": "sequential_elo", "raw_elo": 1450.2105516399035, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.59079929471259, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 15.179828253878972, "unilateral_faults": 0, "wins": 57 }, { "admitted_plugins": 4, "attempted_matches": 186, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 93, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 99, "max_score": null, "measured_at": "2026-07-27T11:08:01Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1459.0362386270358, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.34286812733045, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 28.80651466885331, "unilateral_faults": 0, "wins": 87 }, { "admitted_plugins": 1, "attempted_matches": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 38, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T11:44:21Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1441.2006518851858, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.70088877553203, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 37 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T11:07:20Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1543.0508772303117, "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.69357520783093, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 68.15703845127177, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugins": 3, "attempted_matches": 194, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 97, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 118, "max_score": null, "measured_at": "2026-07-27T11:21:00Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 194, "rating_method": "sequential_elo", "raw_elo": 1434.423428573234, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.437043207071774, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.98479089078668, "unilateral_faults": 0, "wins": 76 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:07:18Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1442.1903981687146, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.613283334610685, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 27, "max_score": null, "measured_at": "2026-07-27T10:13:57Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1435.9565657354813, "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": "omitted", "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": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.55014764549661, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T10:28:31Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1426.356743667632, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.044276212350354, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T10:13:26Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1416.7106818294349, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.55024026744643, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 33 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:16:10Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1430.2908983914597, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.1919263578203, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T11:24:39Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1407.767805319223, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.48204243070537, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 31 }, { "admitted_plugins": 1, "attempted_matches": 74, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 37, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 48, "max_score": null, "measured_at": "2026-07-27T11:24:40Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1375.3160039220393, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.759058589728017, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 3, "attempted_matches": 188, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 94, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 103, "max_score": null, "measured_at": "2026-07-27T11:21:01Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1377.3912241549654, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.52128553699262, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 19.067326122184195, "unilateral_faults": 0, "wins": 85 }, { "admitted_plugins": 1, "attempted_matches": 74, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 37, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 48, "max_score": null, "measured_at": "2026-07-27T11:07:15Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1340.6671312177457, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.62036218416104, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 3, "attempted_matches": 196, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 98, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 136, "max_score": null, "measured_at": "2026-07-27T11:21:01Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 196, "rating_method": "sequential_elo", "raw_elo": 1342.0283612027545, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.419157365923827, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.792154980996397, "unilateral_faults": 0, "wins": 60 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:06:11Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1343.9306693331305, "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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.5579502972611, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T11:24:44Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1306.4883081561472, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.93738491295836, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 22 }, { "admitted_plugins": 2, "attempted_matches": 140, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 70, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 98, "max_score": null, "measured_at": "2026-07-27T11:10:14Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 140, "rating_method": "sequential_elo", "raw_elo": 1301.7070258578517, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.811735212142757, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 15.606750070474943, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T11:10:14Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1305.284761574915, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 20.941820909912263, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 65, "max_score": null, "measured_at": "2026-07-26T02:17:58Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1243.4154165469658, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 13.059186845663168, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 15 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 53, "max_score": null, "measured_at": "2026-07-27T11:24:40Z", "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": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1123.6908903432654, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 0.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 5 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T10:41:53Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1772.6067863963965, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 88.32799956129024, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 17, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1750.2486128915534, "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 83.5076304126712, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T11:52:34Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1666.5668321788196, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 74.39181497022835, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 40 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:52:23Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1628.545670896392, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 69.18453151488029, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 35 }, { "admitted_plugins": 2, "attempted_matches": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 38, "draws": 8, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1610.797508914191, "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 65.37732935727273, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 35.86719719448568, "unilateral_faults": 0, "wins": 70 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-26T02:17:56Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1597.3872665406357, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 63.74719915833959, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 48 }, { "admitted_plugins": 3, "attempted_matches": 178, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 89, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 74, "max_score": null, "measured_at": "2026-07-27T11:52:32Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 178, "rating_method": "sequential_elo", "raw_elo": 1551.392329535351, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 59.05974856700104, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 20.644329938565026, "unilateral_faults": 0, "wins": 102 }, { "admitted_plugins": 2, "attempted_matches": 130, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 65, "draws": 12, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 65, "max_score": null, "measured_at": "2026-07-27T10:41:44Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 130, "rating_method": "sequential_elo", "raw_elo": 1499.236810439388, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.38713921457689, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.801044736378422, "unilateral_faults": 0, "wins": 53 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T10:40:00Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1508.2219156109704, "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": "omitted", "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": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.81947406397143, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 18 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 3, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:36:11Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1494.5099950724373, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.49077663608371, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 1, "attempted_matches": 42, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 21, "draws": 8, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 16, "max_score": null, "measured_at": "2026-07-27T10:36:17Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1498.497941533217, "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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.71534315686365, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 2, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 34, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 50, "max_score": null, "measured_at": "2026-07-27T11:44:21Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1527.6744919780415, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.44356696704924, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 53.9669329725016, "unilateral_faults": 0, "wins": 51 }, { "admitted_plugins": 3, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 81, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 84, "max_score": null, "measured_at": "2026-07-27T11:52:36Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1466.9886937713543, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.43562893658869, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 23.759481979378876, "unilateral_faults": 0, "wins": 78 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T11:52:32Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1467.99966969457, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.15146009630666, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 34, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1455.789381704686, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 46.195935526761325, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 23 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T08:28:44Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1452.7547853739904, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.905146597643856, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 4, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 81, "draws": 13, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 86, "max_score": null, "measured_at": "2026-07-27T10:41:53Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1441.9272292669764, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.00034064191036, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 33.87748199980286, "unilateral_faults": 0, "wins": 63 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T10:38:32Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1418.0209855099072, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.47292470469752, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 25 }, { "admitted_plugins": 1, "attempted_matches": 84, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 42, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 49, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 84, "rating_method": "sequential_elo", "raw_elo": 1408.9987545376268, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.09911159247618, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 34 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T10:38:30Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1420.038975375964, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.02316688669191, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 20 }, { "admitted_plugins": 3, "attempted_matches": 186, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 93, "draws": 8, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 94, "max_score": null, "measured_at": "2026-07-27T11:52:36Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1402.4748118054893, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.26711538483674, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 19.446476867543144, "unilateral_faults": 0, "wins": 84 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T10:38:34Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1400.355913354061, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.65939289391045, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 24 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 17, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:44:14Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1395.505080795559, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.05328535902041, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1357.4859927674747, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.27058263129217, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 23 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T08:28:47Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1365.0587937088449, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.66842106080365, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 15 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:44:23Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1354.7769806450185, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.299677169988506, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 10, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 47, "max_score": null, "measured_at": "2026-07-26T02:16:28Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1362.173682387377, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.28247725695701, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 23 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 44, "max_score": null, "measured_at": "2026-07-27T11:44:24Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1347.1351283730276, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.776314936759203, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 16 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-27T10:38:38Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1345.003199893997, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.60074877484011, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 27 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 40, "max_score": null, "measured_at": "2026-07-27T11:44:17Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1338.9971736131567, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.7973175132515, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 20 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 5, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:52:31Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1331.884389148848, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.736210534597397, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 23 }, { "admitted_plugins": 2, "attempted_matches": 106, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 53, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 72, "max_score": null, "measured_at": "2026-07-27T11:52:32Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 106, "rating_method": "sequential_elo", "raw_elo": 1292.7620567863044, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.06381411034904, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 24.370311027326338, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugins": 2, "attempted_matches": 124, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 62, "draws": 3, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 92, "max_score": null, "measured_at": "2026-07-27T10:41:56Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 124, "rating_method": "sequential_elo", "raw_elo": 1247.794253674446, "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": 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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 18.594475422927697, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 29 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 45, "max_score": null, "measured_at": "2026-07-27T11:52:33Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1184.250882263081, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 9.62312811760228, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T10:30:49Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1741.5924576205412, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 78.91131680197287, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T11:36:21Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1730.8896425336536, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 78.20945134532496, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 42 }, { "admitted_plugins": 2, "attempted_matches": 74, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 37, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T11:36:24Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1716.6223916896186, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 74.68590448880083, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 34.14738066126455, "unilateral_faults": 0, "wins": 96 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T11:36:22Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1657.169899748788, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 68.47656737578293, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 42 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 27, "max_score": null, "measured_at": "2026-07-26T05:17:45Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1648.2434811975372, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 66.08096329718745, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 31.007726186437235, "unilateral_faults": 0, "wins": 61 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:36:23Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1636.5407743062012, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 65.31899895038302, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:54:26Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1585.6437673215585, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 59.132337083693706, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 37 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-26T05:19:02Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1594.7046977870536, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 59.08661445196189, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 31.007726186437235, "unilateral_faults": 0, "wins": 51 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:30:07Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1573.8998861000514, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.49104851229338, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 29 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T11:54:22Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1563.6722330880127, "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": "omitted", "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": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.05572388516481, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 2, "attempted_matches": 134, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 67, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 67, "max_score": null, "measured_at": "2026-07-27T11:54:26Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 134, "rating_method": "sequential_elo", "raw_elo": 1541.7067569374103, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.638525271468005, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 16.888824360518605, "unilateral_faults": 0, "wins": 67 }, { "admitted_plugins": 3, "attempted_matches": 134, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 67, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 61, "max_score": null, "measured_at": "2026-07-27T11:55:02Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 134, "rating_method": "sequential_elo", "raw_elo": 1551.187140315273, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.48050971680028, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 30.25123141631108, "unilateral_faults": 0, "wins": 73 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:37:27Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1507.216526715812, "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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.68030592612551, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-27T08:38:34Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1496.914059374072, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.433559455600474, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 27 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:24:42Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1484.101949958685, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.759775387566016, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 29 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T07:48:11Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1456.9711745696457, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.21538951578612, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32 }, { "admitted_plugins": 3, "attempted_matches": 196, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 98, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 109, "max_score": null, "measured_at": "2026-07-27T11:36:24Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 196, "rating_method": "sequential_elo", "raw_elo": 1428.0841806139645, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.6894460221831, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.89670599806736, "unilateral_faults": 0, "wins": 87 }, { "admitted_plugins": 2, "attempted_matches": 130, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 65, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 68, "max_score": null, "measured_at": "2026-07-27T11:18:25Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 130, "rating_method": "sequential_elo", "raw_elo": 1426.8494348714175, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.538135675658424, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.801044736378422, "unilateral_faults": 0, "wins": 62 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T11:24:42Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1427.2591466449226, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.33378677910713, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 30 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T11:30:08Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1424.7213899013211, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.889795026123, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 2, "attempted_matches": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 38, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 64, "max_score": null, "measured_at": "2026-07-27T11:36:22Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1475.770927184747, "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.591336171666406, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 51.78081388532118, "unilateral_faults": 0, "wins": 54 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:36:22Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1426.1484616915282, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.25705460545867, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T10:37:45Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1460.8792605596052, "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.62676198026428, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 67.16844047215152, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 2, "attempted_matches": 132, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 66, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 76, "max_score": null, "measured_at": "2026-07-27T11:30:00Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 132, "rating_method": "sequential_elo", "raw_elo": 1402.083848243849, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.29726259726838, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.85345304153558, "unilateral_faults": 0, "wins": 56 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T11:30:08Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1394.6909165849377, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.07904754522137, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 2, "attempted_matches": 126, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 63, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 76, "max_score": null, "measured_at": "2026-07-27T11:36:24Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 126, "rating_method": "sequential_elo", "raw_elo": 1378.8097448915178, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.157624044502754, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 18.8015810723003, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 42, "max_score": null, "measured_at": "2026-07-27T10:15:58Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1358.1292477360432, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.609212884277255, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 18, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T11:30:07Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1369.5464379088992, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.89400329893377, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 36, "max_score": null, "measured_at": "2026-07-27T10:13:26Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1349.90531693581, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.115764310136107, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 22 }, { "admitted_plugins": 2, "attempted_matches": 130, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 63, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 90, "max_score": null, "measured_at": "2026-07-27T11:36:23Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 130, "rating_method": "sequential_elo", "raw_elo": 1339.7266305359385, "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": "other", "provider_model": "cohere/north-mini-code", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.1563438776522, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.801044736378422, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 3, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 90, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 125, "max_score": null, "measured_at": "2026-07-27T11:36:24Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1297.2587401740643, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.382657975617843, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 19.960087583821387, "unilateral_faults": 0, "wins": 57 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 34, "max_score": null, "measured_at": "2026-07-27T10:36:04Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1301.0437601099366, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 20.745733263714285, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 36, "max_score": null, "measured_at": "2026-07-27T11:30:07Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1272.023445307137, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 18.05367245403799, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 24 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 46, "max_score": null, "measured_at": "2026-07-27T11:36:23Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1245.2596467020408, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 14.557228718434729, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 14 }, { "admitted_plugins": 1, "attempted_matches": 42, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 21, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T10:36:04Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1143.6148913795123, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 0.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 2, "attempted_matches": 72, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 36, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:44:35Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 72, "rating_method": "sequential_elo", "raw_elo": 1697.0145305689157, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 64.68307799655075, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 35.894862185116764, "unilateral_faults": 0, "wins": 86 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T10:44:31Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1649.3609751746642, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 59.81731792757247, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 49 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T11:18:24Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1637.7826189897944, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.91782061761204, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 29 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 6, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T10:59:39Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1636.0494722351684, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.75514722037097, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 45 }, { "admitted_plugins": 2, "attempted_matches": 72, "capped_draws": 11, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 36, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:44:26Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 72, "rating_method": "sequential_elo", "raw_elo": 1627.714306163753, "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.69099122402372, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 52.34956811791491, "unilateral_faults": 0, "wins": 84 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T09:25:52Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1564.7574379284083, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.85724479955294, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 31 }, { "admitted_plugins": 3, "attempted_matches": 132, "capped_draws": 40, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 66, "draws": 40, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T11:18:24Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 132, "rating_method": "sequential_elo", "raw_elo": 1536.5996659469154, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.46538459256074, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 5, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 5, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T10:44:32Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1522.545055470742, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.45816504693588, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 32 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-27T10:52:42Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1499.683273236858, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.413437929557105, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugins": 4, "attempted_matches": 262, "capped_draws": 172, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 131, "draws": 172, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 46, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 262, "rating_method": "sequential_elo", "raw_elo": 1473.5547148296998, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.3268240179212, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.648363361490077, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugins": 1, "attempted_matches": 74, "capped_draws": 47, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 37, "draws": 47, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T11:59:32Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1456.5863157614344, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.15214880984472, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 5 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 49, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 49, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T08:31:12Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1454.9766570016957, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.70399047704974, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 10 }, { "admitted_plugins": 1, "attempted_matches": 80, "capped_draws": 65, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 40, "draws": 65, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T10:42:50Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1450.2389966102576, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.438953458145875, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 53, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 53, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1449.6896851314627, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.668609009228703, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 49, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 49, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T10:09:50Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1450.883258777918, "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": "other", "provider_model": "cohere/north-mini-code", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.6168805991318, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 57, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 57, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1446.802549177008, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.33186721946456, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 56, "capped_draws": 45, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 45, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:40:50Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1448.3295730196996, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.82065391961682, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 3 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 38, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T10:53:39Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1452.3898563879034, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.41990029819383, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 3, "attempted_matches": 184, "capped_draws": 131, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 92, "draws": 131, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 184, "rating_method": "sequential_elo", "raw_elo": 1441.7341102563012, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.13021040956949, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 19.803385417785595, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 50, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:59:32Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1441.8619859707171, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.959030783411738, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 56, "capped_draws": 48, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 48, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1440.8610223975368, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.6636526111786, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1 }, { "admitted_plugins": 3, "attempted_matches": 196, "capped_draws": 155, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 98, "draws": 155, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:59:44Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 196, "rating_method": "sequential_elo", "raw_elo": 1436.75553312595, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.61960427875735, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 17.700176346389366, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 42, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 42, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T10:53:41Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1446.1686024506469, "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": "omitted", "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": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.45612575749886, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 43, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 43, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T10:52:42Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1439.4942097257222, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.304012940866215, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 52, "capped_draws": 47, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 26, "draws": 47, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-27T10:42:48Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 52, "rating_method": "sequential_elo", "raw_elo": 1438.2888976809872, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.961097857676517, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 2, "attempted_matches": 136, "capped_draws": 111, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 68, "draws": 111, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T10:53:39Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 136, "rating_method": "sequential_elo", "raw_elo": 1427.1095998713513, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.27875377434565, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 16.461902543922633, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 30, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 18, "draws": 30, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T10:42:48Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1440.4422887134535, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.61921497496216, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 2, "attempted_matches": 138, "capped_draws": 111, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 69, "draws": 111, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T10:59:43Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 138, "rating_method": "sequential_elo", "raw_elo": 1420.8052557973035, "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": 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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.35282742604081, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 16.05264788810895, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 57, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-26T02:18:08Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1434.5293603256966, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.212894203087245, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 2, "attempted_matches": 140, "capped_draws": 113, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 70, "draws": 113, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T10:51:51Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 140, "rating_method": "sequential_elo", "raw_elo": 1416.3710347575352, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 23.723344738770017, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 27, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 27, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T10:59:38Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1418.016037894468, "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": "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.47989431367969, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 2, "attempted_matches": 120, "capped_draws": 97, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 60, "draws": 97, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T10:42:49Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 120, "rating_method": "sequential_elo", "raw_elo": 1409.1936649870358, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.028323800205285, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 20.294267162641567, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 63, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 16, "max_score": null, "measured_at": "2026-07-26T01:24:45Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1418.4072460856055, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.7153135861437, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 28, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 18, "draws": 28, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:42:43Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1405.73919833146, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 19.24313559757037, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 15, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T10:42:50Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1479.2279924952009, "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "requested_reasoning_effort": "low" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 17.83316943117343, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/baseline", "track_name": "Baseline filter", "uncertainty": 69.22474682633933, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 8, "attempted_matches": 462, "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-2026-07-25": 11 }, "run_count": 8, "token_priced_attempt_count": 11, "total": 12.66097 }, "codegen_evaluated_cells": 8, "conditional_success_score": 83.35493107640038, "contributing_entrants": null, "distinct_rated_opponents": 231, "draws": 65, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04" ], "infra_failures_excluded": 4, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:46:35Z", "losses": 78, "max_score": 100.0, "measured_at": null, "min_score": 61.59421983387494, "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 462, "rating_method": "sequential_elo", "raw_elo": 1732.2058050532637, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 83.35493107640038, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 319 }, { "admitted_plugins": 13, "attempted_matches": 520, "capped_draws": 0, "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": 1.320515, "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": 77.44179232176744, "contributing_entrants": null, "distinct_rated_opponents": 260, "draws": 40, "entry_count": 13, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-26T05:19:34Z", "losses": 100, "max_score": 99.01057790596052, "measured_at": null, "min_score": 63.18013490216033, "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 520, "rating_method": "sequential_elo", "raw_elo": 1757.36248030638, "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" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 73.52435752053414, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 380 }, { "admitted_plugins": 8, "attempted_matches": 486, "capped_draws": 22, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 9 }, "evidence_basis": "Standard list-price estimate", "max": 3.2933475, "mean": 2.642580625, "median": 2.681945, "min": 1.562975, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 21.140644999999996 }, "codegen_evaluated_cells": 8, "conditional_success_score": 71.82613215131099, "contributing_entrants": null, "distinct_rated_opponents": 243, "draws": 101, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:53:35Z", "losses": 87, "max_score": 100.0, "measured_at": null, "min_score": 38.52438727472494, "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 486, "rating_method": "sequential_elo", "raw_elo": 1705.7578706039046, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 71.82613215131099, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 298 }, { "admitted_plugins": 7, "attempted_matches": 430, "capped_draws": 30, "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-2026-07-25": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 21.885474999999996 }, "codegen_evaluated_cells": 8, "conditional_success_score": 67.9471088226076, "contributing_entrants": null, "distinct_rated_opponents": 215, "draws": 95, "entry_count": 7, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:37:21Z", "losses": 94, "max_score": 88.73890042665397, "measured_at": null, "min_score": 30.738052083219, "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 429, "rating_method": "sequential_elo", "raw_elo": 1678.5115903938529, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 65.71628362373028, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 240 }, { "admitted_plugins": 8, "attempted_matches": 488, "capped_draws": 12, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 8 }, "evidence_basis": "Standard list-price estimate", "max": 12.915325, "mean": 10.059243749999998, "median": 10.0094025, "min": 8.401555, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 80.47395 }, "codegen_evaluated_cells": 8, "conditional_success_score": 65.25243558332285, "contributing_entrants": null, "distinct_rated_opponents": 244, "draws": 58, "entry_count": 8, "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 }, "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": "2026-07-27T11:45:56Z", "losses": 137, "max_score": 100.0, "measured_at": null, "min_score": 16.21797777560009, "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 488, "rating_method": "sequential_elo", "raw_elo": 1631.458664413848, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 65.25243558332285, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 293 }, { "admitted_plugins": 8, "attempted_matches": 492, "capped_draws": 21, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 11 }, "evidence_basis": "Standard list-price estimate", "max": 12.13752, "mean": 8.1660015625, "median": 8.18098, "min": 4.7142525, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 11 }, "run_count": 8, "token_priced_attempt_count": 11, "total": 65.3280125 }, "codegen_evaluated_cells": 8, "conditional_success_score": 54.627943464276825, "contributing_entrants": null, "distinct_rated_opponents": 246, "draws": 96, "entry_count": 8, "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 }, "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": "2026-07-27T11:53:51Z", "losses": 167, "max_score": 72.98349769903467, "measured_at": null, "min_score": 42.877873486874975, "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 492, "rating_method": "sequential_elo", "raw_elo": 1576.1527501926316, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 54.627943464276825, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 229 }, { "admitted_plugins": 8, "attempted_matches": 470, "capped_draws": 7, "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": 4.987857, "mean": 3.1645696249999995, "median": 3.0710854999999997, "min": 1.985613, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 10 }, "run_count": 9, "token_priced_attempt_count": 10, "total": 28.806540999999996 }, "codegen_evaluated_cells": 9, "conditional_success_score": 51.77615652783872, "contributing_entrants": null, "distinct_rated_opponents": 235, "draws": 132, "entry_count": 8, "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 }, "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": "2026-07-27T11:37:21Z", "losses": 154, "max_score": 75.31262484978316, "measured_at": null, "min_score": 28.573734971782702, "model_code_failure_rate": 0.1111111111111111, "model_code_failures": 1, "model_display_name": "GPT-5.6 Luna", "model_slug": "gpt-5-6-luna", "plugin_success_rate": 0.8888888888888888, "provider": "OpenAI", "provider_key": "openai", "rank": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 470, "rating_method": "sequential_elo", "raw_elo": 1558.4439764910153, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 1, "repaired_rate": 0.1111111111111111, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 50.27379592979224, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 184 }, { "admitted_plugins": 20, "attempted_matches": 716, "capped_draws": 18, "codegen_cost_usd": { "admitted_cell_count": 20, "cell_count": 8, "cost_basis_counts": { "provider_reported": 37 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.14454373333333334, "mean": 0.08818255, "median": 0.07401653333333333, "min": 0.052337466666666665, "recorded_attempt_count": 37, "run_count": 24, "total": 2.1163812 }, "codegen_evaluated_cells": 24, "conditional_success_score": 51.65268475219032, "contributing_entrants": null, "distinct_rated_opponents": 358, "draws": 257, "entry_count": 40, "failed_game_aliases": [ "GB2-02", "GB2-03", "GB2-05" ], "first_pass_admitted": 12, "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 }, "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": "2026-07-27T11:53:35Z", "losses": 472, "max_score": 64.63299103911847, "measured_at": null, "min_score": 22.814064655201765, "model_code_failure_rate": 0.16666666666666666, "model_code_failures": 4, "model_display_name": "Grok 4.5", "model_slug": "x-ai-grok-4-5", "plugin_success_rate": 0.8333333333333334, "provider": "xAI", "provider_key": "x-ai", "rank": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 716, "rating_method": "sequential_elo", "raw_elo": 1562.5568848125563, "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" }, "repaired_admitted": 8, "repaired_rate": 0.3333333333333333, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 49.35118534448464, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 697 }, { "admitted_plugins": 7, "attempted_matches": 422, "capped_draws": 6, "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-2026-07-25": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 7.44989 }, "codegen_evaluated_cells": 8, "conditional_success_score": 49.82574174672981, "contributing_entrants": null, "distinct_rated_opponents": 211, "draws": 59, "entry_count": 7, "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 }, "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": "2026-07-27T11:53:30Z", "losses": 123, "max_score": 49.82574174672981, "measured_at": null, "min_score": 49.82574174672981, "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 422, "rating_method": "sequential_elo", "raw_elo": 1636.395785460338, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 48.18987346377536, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 240 }, { "admitted_plugins": 18, "attempted_matches": 726, "capped_draws": 80, "codegen_cost_usd": { "admitted_cell_count": 18, "cell_count": 8, "cost_basis_counts": { "provider_reported": 48 }, "evidence_basis": "Provider-reported", "failed_cell_count": 5, "max": 0.9392418, "mean": 0.7382814249999998, "median": 0.7264120999999999, "min": 0.4980382, "recorded_attempt_count": 48, "run_count": 23, "total": 16.779512399999998 }, "codegen_evaluated_cells": 23, "conditional_success_score": 50.66737638021479, "contributing_entrants": null, "distinct_rated_opponents": 363, "draws": 412, "entry_count": 36, "failed_game_aliases": [ "GB2-03", "GB2-05", "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 }, "infra_excluded_game_aliases": [ "GB2-02", "GB2-08" ], "infra_failures_excluded": 3, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:54:18Z", "losses": 407, "max_score": 53.439927382671186, "measured_at": null, "min_score": 46.192829786225445, "model_code_failure_rate": 0.21739130434782608, "model_code_failures": 5, "model_display_name": "Kimi K3", "model_slug": "moonshotai-kimi-k3", "plugin_success_rate": 0.782608695652174, "provider": "Moonshot", "provider_key": "moonshotai", "rank": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 725, "rating_method": "sequential_elo", "raw_elo": 1535.4007037331653, "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" }, "repaired_admitted": 18, "repaired_rate": 0.782608695652174, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 47.65567044796971, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 528 }, { "admitted_plugins": 12, "attempted_matches": 762, "capped_draws": 56, "codegen_cost_usd": { "admitted_cell_count": 12, "cell_count": 7, "cost_basis_counts": { "local_standard_estimate": 15 }, "evidence_basis": "Standard list-price estimate", "max": 1.5164726249999998, "mean": 1.0182428035714286, "median": 0.9670455, "min": 0.8356068750000001, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 15 }, "run_count": 12, "token_priced_attempt_count": 15, "total": 12.214044 }, "codegen_evaluated_cells": 12, "conditional_success_score": 46.5489701837238, "contributing_entrants": null, "distinct_rated_opponents": 381, "draws": 205, "entry_count": 12, "failed_game_aliases": [], "first_pass_admitted": 10, "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 }, "infra_excluded_game_aliases": [ "GB2-01", "GB2-03", "GB2-04" ], "infra_failures_excluded": 6, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:53:30Z", "losses": 271, "max_score": 66.30476749736133, "measured_at": null, "min_score": 29.44411630713003, "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 762, "rating_method": "sequential_elo", "raw_elo": 1521.9931594970951, "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-mini", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 2, "repaired_rate": 0.16666666666666666, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 46.5489701837238, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 286 }, { "admitted_plugins": 10, "attempted_matches": 620, "capped_draws": 62, "codegen_cost_usd": { "admitted_cell_count": 10, "cell_count": 8, "cost_basis_counts": { "local_list_price_estimate": 10 }, "evidence_basis": "Standard list-price estimate", "max": 0.4567, "mean": 0.3660333333333334, "median": 0.355077, "min": 0.234622, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 2, "boardgame-list-prices-2026-07-25": 8 }, "run_count": 10, "token_priced_attempt_count": 10, "total": 3.5443079999999996 }, "codegen_evaluated_cells": 10, "conditional_success_score": 44.835133203247864, "contributing_entrants": null, "distinct_rated_opponents": 310, "draws": 194, "entry_count": 10, "failed_game_aliases": [], "first_pass_admitted": 10, "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 }, "infra_excluded_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "GB2-05", "GB2-06", "GB2-07", "GB2-08" ], "infra_failures_excluded": 18, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:48:31Z", "losses": 217, "max_score": 58.84535558133786, "measured_at": null, "min_score": 31.86645017234374, "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": 620, "rating_method": "sequential_elo", "raw_elo": 1507.2177594422292, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 44.835133203247864, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 209 }, { "admitted_plugins": 6, "attempted_matches": 384, "capped_draws": 66, "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": 45.7754669580277, "contributing_entrants": null, "distinct_rated_opponents": 192, "draws": 90, "entry_count": 6, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:53:51Z", "losses": 144, "max_score": 76.49983872640665, "measured_at": null, "min_score": 23.38150584800255, "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": 384, "rating_method": "sequential_elo", "raw_elo": 1522.0401416715802, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 42.598871978808184, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 150 }, { "admitted_plugins": 8, "attempted_matches": 294, "capped_draws": 35, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 10 }, "evidence_basis": "Standard list-price estimate", "max": 0.454645, "mean": 0.28201406249999994, "median": 0.2695775, "min": 0.17401125, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 10 }, "run_count": 8, "token_priced_attempt_count": 10, "total": 2.2561125 }, "codegen_evaluated_cells": 8, "conditional_success_score": 42.010776110623965, "contributing_entrants": null, "distinct_rated_opponents": 147, "draws": 166, "entry_count": 16, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:54:22Z", "losses": 172, "max_score": 62.019294143192774, "measured_at": null, "min_score": 24.622792993226422, "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": 293, "rating_method": "sequential_elo", "raw_elo": 1518.3720508554893, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 42.010776110623965, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 1, "wins": 183 }, { "admitted_plugins": 15, "attempted_matches": 954, "capped_draws": 144, "codegen_cost_usd": { "admitted_cell_count": 15, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 25 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 2, "max": 0.38568888333333334, "mean": 0.29249454166666666, "median": 0.2834616125, "min": 0.2238526, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 25 }, "run_count": 17, "token_priced_attempt_count": 25, "total": 5.07700365 }, "codegen_evaluated_cells": 17, "conditional_success_score": 42.56690883616381, "contributing_entrants": null, "distinct_rated_opponents": 477, "draws": 316, "entry_count": 15, "failed_game_aliases": [ "GB2-02", "GB2-03" ], "first_pass_admitted": 10, "first_pass_rate": 0.5882352941176471, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [ "GB2-01", "GB2-03", "GB2-04", "GB2-05", "GB2-06", "GB2-07" ], "infra_failures_excluded": 9, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:47:56Z", "losses": 336, "max_score": 42.56690883616381, "measured_at": null, "min_score": 42.56690883616381, "model_code_failure_rate": 0.1176470588235294, "model_code_failures": 2, "model_display_name": "GPT-5.4 Nano", "model_slug": "gpt-5-4-nano", "plugin_success_rate": 0.8823529411764706, "provider": "OpenAI", "provider_key": "openai", "rank": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 953, "rating_method": "sequential_elo", "raw_elo": 1505.1823030253686, "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-nano", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 5, "repaired_rate": 0.29411764705882354, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 41.25558005932039, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 1, "wins": 301 }, { "admitted_plugins": 6, "attempted_matches": 200, "capped_draws": 25, "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": 0.4890770625000001, "median": 0.483741, "min": 0.401826, "recorded_attempt_count": 18, "run_count": 8, "total": 3.912616499999999 }, "codegen_evaluated_cells": 8, "conditional_success_score": 41.30954240884414, "contributing_entrants": null, "distinct_rated_opponents": 100, "draws": 113, "entry_count": 12, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:53:34Z", "losses": 130, "max_score": 66.37931618441283, "measured_at": null, "min_score": 18.44050863736999, "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 200, "rating_method": "sequential_elo", "raw_elo": 1511.5059865373096, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 38.442860892954606, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 121 }, { "admitted_plugins": 19, "attempted_matches": 1197, "capped_draws": 164, "codegen_cost_usd": { "admitted_cell_count": 19, "cell_count": 8, "cost_basis_counts": { "provider_reported": 57 }, "evidence_basis": "Provider-reported", "failed_cell_count": 8, "max": 0.25293804044999996, "mean": 0.19953128278325, "median": 0.20662718916666667, "min": 0.13279406625, "recorded_attempt_count": 57, "run_count": 27, "total": 5.24138213703 }, "codegen_evaluated_cells": 27, "conditional_success_score": 41.66158464393463, "contributing_entrants": null, "distinct_rated_opponents": 599, "draws": 428, "entry_count": 19, "failed_game_aliases": [ "GB2-01", "GB2-03", "GB2-04", "GB2-06" ], "first_pass_admitted": 1, "first_pass_rate": 0.037037037037037035, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [ "GB2-03", "GB2-06" ], "infra_failures_excluded": 2, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:55:02Z", "losses": 392, "max_score": 57.37331813393658, "measured_at": null, "min_score": 30.05739733199343, "model_code_failure_rate": 0.2962962962962963, "model_code_failures": 8, "model_display_name": "GLM-5.2", "model_slug": "z-ai-glm-5-2", "plugin_success_rate": 0.7037037037037037, "provider": "Zhipu", "provider_key": "z-ai", "rank": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1197, "rating_method": "sequential_elo", "raw_elo": 1516.1537157939886, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 18, "repaired_rate": 0.6666666666666666, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 38.15779267423163, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 377 }, { "admitted_plugins": 16, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 16, "cell_count": 8, "cost_basis_counts": { "provider_reported": 34 }, "evidence_basis": "Provider-reported", "max": 0.04815395, "mean": 0.0408814375, "median": 0.040641, "min": 0.0341807, "recorded_attempt_count": 34, "run_count": 16, "total": 0.654103 }, "codegen_evaluated_cells": 16, "conditional_success_score": 37.08427156622473, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": 232, "entry_count": 16, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-26T04:34:09Z", "losses": 230, "max_score": 53.91719217050105, "measured_at": null, "min_score": 25.25796091549614, "model_code_failure_rate": 0.0, "model_code_failures": 0, "model_display_name": "Gemini 3.5 Flash Lite", "model_slug": "google-gemini-3-5-flash-lite", "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": 0, "rating_method": "sequential_elo", "raw_elo": 1468.5191981065773, "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" }, "repaired_admitted": 16, "repaired_rate": 1.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 37.08427156622473, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 11, "attempted_matches": 694, "capped_draws": 78, "codegen_cost_usd": { "admitted_cell_count": 11, "cell_count": 8, "cost_basis_counts": { "provider_reported": 26 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.015971877, "mean": 0.00979196948, "median": 0.009500477, "min": 0.003562685, "recorded_attempt_count": 26, "run_count": 15, "total": 0.14255357568000002 }, "codegen_evaluated_cells": 15, "conditional_success_score": 37.57837372308959, "contributing_entrants": null, "distinct_rated_opponents": 347, "draws": 182, "entry_count": 11, "failed_game_aliases": [ "GB2-03", "GB2-04" ], "first_pass_admitted": 5, "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 }, "infra_excluded_game_aliases": [ "GB2-08" ], "infra_failures_excluded": 1, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:53:45Z", "losses": 310, "max_score": 49.87227457080003, "measured_at": null, "min_score": 30.214944656619977, "model_code_failure_rate": 0.26666666666666666, "model_code_failures": 4, "model_display_name": "DeepSeek V4 Flash", "model_slug": "deepseek-deepseek-v4-flash", "plugin_success_rate": 0.7333333333333333, "provider": "DeepSeek", "provider_key": "deepseek", "rank": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 694, "rating_method": "sequential_elo", "raw_elo": 1439.838020168251, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": 6, "repaired_rate": 0.4, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 34.77469565398564, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 202 }, { "admitted_plugins": 5, "attempted_matches": 202, "capped_draws": 32, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 18 }, "evidence_basis": "Provider-reported", "failed_cell_count": 3, "max": 0.01660212, "mean": 0.00855959175, "median": 0.005979701, "min": 0.00271606, "recorded_attempt_count": 18, "run_count": 8, "total": 0.068476734 }, "codegen_evaluated_cells": 8, "conditional_success_score": 33.62820028985485, "contributing_entrants": null, "distinct_rated_opponents": 101, "draws": 150, "entry_count": 10, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:46:17Z", "losses": 104, "max_score": 60.76783956869306, "measured_at": null, "min_score": 19.179163036226186, "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 202, "rating_method": "sequential_elo", "raw_elo": 1476.6748561574834, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 29.900168086056908, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 7, "attempted_matches": 252, "capped_draws": 13, "codegen_cost_usd": { "admitted_cell_count": 7, "cell_count": 8, "cost_basis_counts": { "provider_reported": 13 }, "evidence_basis": "Provider-reported", "failed_cell_count": 2, "max": 0.0056201515, "mean": 0.0029446039375, "median": 0.001956843, "min": 0.001266762, "recorded_attempt_count": 13, "run_count": 9, "total": 0.029176982999999997 }, "codegen_evaluated_cells": 9, "conditional_success_score": 29.32204005563696, "contributing_entrants": null, "distinct_rated_opponents": 126, "draws": 130, "entry_count": 14, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:37:26Z", "losses": 208, "max_score": 51.729550125281335, "measured_at": null, "min_score": 18.058264435137527, "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 252, "rating_method": "sequential_elo", "raw_elo": 1453.3749708580128, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 2, "repaired_rate": 0.2222222222222222, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 27.53645729515707, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 144 }, { "admitted_plugins": 5, "attempted_matches": 188, "capped_draws": 29, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 18 }, "evidence_basis": "Provider-reported", "failed_cell_count": 3, "max": 0.08193244999999999, "mean": 0.05495368125, "median": 0.056941025, "min": 0.02174195, "recorded_attempt_count": 18, "run_count": 8, "total": 0.43962945 }, "codegen_evaluated_cells": 8, "conditional_success_score": 30.663694734085283, "contributing_entrants": null, "distinct_rated_opponents": 94, "draws": 59, "entry_count": 10, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:46:13Z", "losses": 179, "max_score": 40.40736615648161, "measured_at": null, "min_score": 19.617975464814673, "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1404.3049647259802, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 27.2643084906714, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 92 }, { "admitted_plugins": 9, "attempted_matches": 333, "capped_draws": 63, "codegen_cost_usd": { "admitted_cell_count": 9, "cell_count": 8, "cost_basis_counts": { "provider_reported": 33 }, "evidence_basis": "Provider-reported", "failed_cell_count": 7, "max": 0.039679950000000005, "mean": 0.029276065625, "median": 0.0306386, "min": 0.01864685, "recorded_attempt_count": 33, "run_count": 16, "total": 0.46841705 }, "codegen_evaluated_cells": 16, "conditional_success_score": 27.60265191197351, "contributing_entrants": null, "distinct_rated_opponents": 167, "draws": 294, "entry_count": 18, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:37:14Z", "losses": 191, "max_score": 31.89087169341551, "measured_at": null, "min_score": 24.99822893746736, "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 333, "rating_method": "sequential_elo", "raw_elo": 1441.7629523084724, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 7, "repaired_rate": 0.4375, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 23.904597767588164, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 106 }, { "admitted_plugins": 5, "attempted_matches": 167, "capped_draws": 29, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 18 }, "evidence_basis": "Provider-reported", "failed_cell_count": 3, "max": 0.0422995, "mean": 0.0264053125, "median": 0.022682375, "min": 0.01946775, "recorded_attempt_count": 18, "run_count": 8, "total": 0.2112425 }, "codegen_evaluated_cells": 8, "conditional_success_score": 26.571197548255896, "contributing_entrants": null, "distinct_rated_opponents": 84, "draws": 104, "entry_count": 10, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:53:48Z", "losses": 169, "max_score": 37.38497422902105, "measured_at": null, "min_score": 15.144663326584237, "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 167, "rating_method": "sequential_elo", "raw_elo": 1393.3296662380549, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 23.625506750070084, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 62 }, { "admitted_plugins": 8, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "provider_reported": 33 }, "evidence_basis": "Provider-reported", "failed_cell_count": 8, "max": 0.341716425, "mean": 0.30867194062500003, "median": 0.31836633750000004, "min": 0.2745495, "recorded_attempt_count": 33, "run_count": 16, "total": 4.9387510500000005 }, "codegen_evaluated_cells": 16, "conditional_success_score": 62.72324131369825, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": 106, "entry_count": 8, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-26T05:19:08Z", "losses": 59, "max_score": 89.93824120320421, "measured_at": null, "min_score": 35.50824142419229, "model_code_failure_rate": 0.5, "model_code_failures": 8, "model_display_name": "Gemini 3.6 Flash", "model_slug": "google-gemini-3-6-flash", "plugin_success_rate": 0.5, "provider": "Google", "provider_key": "google", "rank": null, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "provisional", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1608.4207637110949, "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" }, "repaired_admitted": 8, "repaired_rate": 0.5, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 52.74374877378255, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 173 }, { "admitted_plugins": 4, "attempted_matches": 158, "capped_draws": 1, "codegen_cost_usd": { "admitted_cell_count": 4, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 8 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 4, "max": 0.055222, "mean": 0.046879, "median": 0.046959, "min": 0.039474, "pricing_table_versions": { "boardgame-list-prices-2026-07-25": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 0.375032 }, "codegen_evaluated_cells": 8, "conditional_success_score": 52.75022683541799, "contributing_entrants": null, "distinct_rated_opponents": 79, "draws": 12, "entry_count": 8, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "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 }, "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": "2026-07-27T11:37:12Z", "losses": 136, "max_score": 51.26533615379074, "measured_at": null, "min_score": 35.574874573353014, "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": 158, "rating_method": "sequential_elo", "raw_elo": 1502.8155544211063, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 44.35747664972328, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 140 }, { "admitted_plugins": 5, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 37 }, "evidence_basis": "Provider-reported", "failed_cell_count": 11, "max": 0.213668025, "mean": 0.180929025625, "median": 0.1746528825, "min": 0.16318875, "recorded_attempt_count": 37, "run_count": 16, "total": 2.89486441 }, "codegen_evaluated_cells": 16, "conditional_success_score": 43.76808690498887, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": 73, "entry_count": 5, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-26T02:15:57Z", "losses": 80, "max_score": 55.633695043376434, "measured_at": null, "min_score": 21.92797491218185, "model_code_failure_rate": 0.6875, "model_code_failures": 11, "model_display_name": "Inkling", "model_slug": "thinkingmachines-inkling", "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": 0, "rating_method": "sequential_elo", "raw_elo": 1440.8641223893603, "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" }, "repaired_admitted": 5, "repaired_rate": 0.3125, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 32.72427770487978, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugins": 5, "attempted_matches": 202, "capped_draws": 68, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 101, "draws": 135, "entry_count": 5, "failed_game_aliases": [], "first_pass_admitted": null, "first_pass_rate": null, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:26:42Z", "losses": 43, "max_score": 51.110878446006915, "measured_at": null, "min_score": 21.605010778009973, "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": "provisional", "rated_matches": 202, "rating_method": "sequential_elo", "raw_elo": 1445.854469940611, "reasoning_level": "Highest", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": null, "requested_effort": "highest", "source": "retained_generation_evidence", "track_id": "full_freedom/intensive" }, "provider_route": "openrouter", "provider_setting_label": "Highest", "reasoning_bracket": "intensive", "reasoning_bucket": "intensive", "reasoning_bucket_label": "Highest", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 31.61899034274135, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": null, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 4, "attempted_matches": 142, "capped_draws": 4, "codegen_cost_usd": { "admitted_cell_count": 4, "cell_count": 8, "cost_basis_counts": { "provider_reported": 13 }, "evidence_basis": "Provider-reported", "failed_cell_count": 5, "max": 0.33185775, "mean": 0.18266821875, "median": 0.16804049999999998, "min": 0.08751, "recorded_attempt_count": 13, "run_count": 9, "total": 1.7932035000000002 }, "codegen_evaluated_cells": 9, "conditional_success_score": 21.2286991885296, "contributing_entrants": null, "distinct_rated_opponents": 71, "draws": 19, "entry_count": 8, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-27T11:30:30Z", "losses": 195, "max_score": 28.364274717844992, "measured_at": null, "min_score": 14.82966031579288, "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": 142, "rating_method": "sequential_elo", "raw_elo": 1304.9356889116953, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": 2, "repaired_rate": 0.2222222222222222, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "track", "score": 17.33316030497761, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T10:51:16Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1902.50819139413, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 58 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 19, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 19, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T10:50:16Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1726.5259512130235, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 77.1650058104334, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 29 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 16, "max_score": null, "measured_at": "2026-07-27T10:47:12Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1715.0185204641425, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 75.5601349974072, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 42 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T10:48:01Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1644.4759251533983, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 66.16530892077893, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugins": 3, "attempted_matches": 98, "capped_draws": 16, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 49, "draws": 34, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 50, "max_score": null, "measured_at": "2026-07-27T10:51:05Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 98, "rating_method": "sequential_elo", "raw_elo": 1645.7131029732216, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 64.63299103911847, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 39.97783371817835, "unilateral_faults": 0, "wins": 126 }, { "admitted_plugins": 2, "attempted_matches": 80, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 40, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-26T05:19:34Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1638.392961019582, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 64.26871280365481, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T10:47:05Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1623.2307722548098, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 63.53247225350247, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 6, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:53:30Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1594.7574022863707, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 59.955367539088286, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 33 }, { "admitted_plugins": 1, "attempted_matches": 76, "capped_draws": 14, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 38, "draws": 14, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:48:31Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1579.7115495088487, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 58.84535558133786, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 43 }, { "admitted_plugins": 3, "attempted_matches": 128, "capped_draws": 22, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 64, "draws": 51, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 85, "max_score": null, "measured_at": "2026-07-27T11:53:12Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 128, "rating_method": "sequential_elo", "raw_elo": 1546.5261237980658, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.36937197174774, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.13401041481541, "unilateral_faults": 0, "wins": 108 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 4, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:53:30Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1534.387956889026, "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-mini", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.12198654872786, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 35 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T10:45:00Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1547.2346974795885, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.729550125281335, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 41.18336395796551, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 2, "attempted_matches": 120, "capped_draws": 68, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 60, "draws": 68, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:55:02Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 120, "rating_method": "sequential_elo", "raw_elo": 1498.2804328508075, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.54578462463877, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 24 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 12, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 12, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 22, "max_score": null, "measured_at": "2026-07-27T10:47:58Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1481.3892527994904, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.46304512513314, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:51:16Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1495.193047600924, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.818716626603695, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 42.70587299553475, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 17, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-26T04:33:46Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1485.3137654013412, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.50093428611456, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 33.41808305530269, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 12, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 12, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T10:47:44Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1472.4808055170065, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.84767304178936, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugins": 2, "attempted_matches": 122, "capped_draws": 30, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 61, "draws": 30, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 53, "max_score": null, "measured_at": "2026-07-27T10:50:15Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 122, "rating_method": "sequential_elo", "raw_elo": 1450.462126069157, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.39685486271934, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 19.7562594006596, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 27, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-26T04:31:49Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1432.9266307142595, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.79869365428509, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 18, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T10:51:06Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1392.986063334523, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.19459609318916, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 46.19324853318743, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 2, "attempted_matches": 118, "capped_draws": 38, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 59, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 64, "max_score": null, "measured_at": "2026-07-27T11:47:56Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 118, "rating_method": "sequential_elo", "raw_elo": 1337.52818990007, "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-nano", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.6338275876808, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 20.80644772842997, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 19, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T10:51:04Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1338.1622966328275, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.74431399881591, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 39.80145244019624, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 42, "capped_draws": 31, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 21, "draws": 31, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T10:30:19Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1308.1269234889603, "reasoning_level": "Highest", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": null, "requested_effort": "highest", "source": "retained_generation_evidence", "track_id": "full_freedom/intensive" }, "provider_route": "openrouter", "provider_setting_label": "Highest", "reasoning_bracket": "intensive", "reasoning_bucket": "intensive", "reasoning_bucket_label": "Highest", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.605010778009973, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 4, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 45, "max_score": null, "measured_at": "2026-07-27T10:50:09Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1302.5506201377443, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 19.617975464814673, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 44.67073949561819, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T11:22:50Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1776.7560641910516, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 43 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 20, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T11:22:56Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1735.4526025988669, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 90.13059941166075, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 35 }, { "admitted_plugins": 2, "attempted_matches": 80, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 40, "draws": 19, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-26T05:18:50Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1697.616249764408, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 78.60604273503697, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 26, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T11:22:53Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1659.3993318565135, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 71.95778371836957, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 29 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 37, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:22:54Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1595.2075134501106, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.20745689293141, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 20 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 37, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:10:04Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1547.1720098303158, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.346922229587115, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 13 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 39, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T07:55:17Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1527.5674418666176, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.24032728154734, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 2, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 33, "draws": 77, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:22:55Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1536.690260686128, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.93697130952252, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 40.69832562925967, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 2, "attempted_matches": 118, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 59, "draws": 104, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T11:10:00Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 118, "rating_method": "sequential_elo", "raw_elo": 1484.4713582365905, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.26185005867806, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 20.80644772842997, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 2, "attempted_matches": 136, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 68, "draws": 116, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T11:23:13Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 136, "rating_method": "sequential_elo", "raw_elo": 1480.838308070823, "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-nano", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.195055758003996, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 16.61455287691689, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 3, "attempted_matches": 175, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 88, "draws": 146, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:17:58Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 175, "rating_method": "sequential_elo", "raw_elo": 1483.9311490852626, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.05739733199343, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 21.200730137000697, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 2, "attempted_matches": 116, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 58, "draws": 105, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T11:22:54Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 116, "rating_method": "sequential_elo", "raw_elo": 1481.5020057636186, "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-mini", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.44411630713003, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 21.37252890985009, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 73, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-26T04:32:26Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1487.3155765144922, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.8476633604157, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 31.75968834662516, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 64, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T11:26:28Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1473.232701299803, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.573734971782702, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 0 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:22:53Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1493.573287927545, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.927667006728253, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 44.39456088374059, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 3, "attempted_matches": 106, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 53, "draws": 169, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T11:18:05Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 106, "rating_method": "sequential_elo", "raw_elo": 1487.5571190487, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.637499866574228, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 38.39228737690977, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-27T11:26:42Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1483.571469812471, "reasoning_level": "Highest", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": null, "requested_effort": "highest", "source": "retained_generation_evidence", "track_id": "full_freedom/intensive" }, "provider_route": "openrouter", "provider_setting_label": "Highest", "reasoning_bracket": "intensive", "reasoning_bucket": "intensive", "reasoning_bucket_label": "Highest", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.082403158201195, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 2, "attempted_matches": 74, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 37, "draws": 113, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:22:56Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 74, "rating_method": "sequential_elo", "raw_elo": 1485.6612365441383, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.918855105037668, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 45.01309903675748, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 37, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 3, "max_score": null, "measured_at": "2026-07-26T02:14:07Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1465.8763415935357, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 23.232137065202014, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 64, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:37:26Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1461.2682908580343, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.27542844920532, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 38.812854461075986, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 53, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:18:01Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1458.3997310867876, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 19.179163036226186, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 46.19324853318743, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 2, "attempted_matches": 80, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 40, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-26T05:19:07Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1818.3922130275887, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 99.01057790596052, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 73 }, { "admitted_plugins": 1, "attempted_matches": 42, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 21, "draws": 20, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T08:03:33Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1640.156750580333, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 69.09378758500024, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 18 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 3, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T08:02:31Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1596.3466678596478, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 61.911144518391616, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 42, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 21, "draws": 11, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T10:19:29Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1548.5258455371809, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.585646325873974, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 18 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 20, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T10:18:25Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 39, "rating_method": "sequential_elo", "raw_elo": 1525.5179367164974, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.31150841617975, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 35.30694150420948, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 17, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-26T02:12:12Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1520.7487899584455, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.6356934973392, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugins": 1, "attempted_matches": 18, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 9, "draws": 35, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T10:19:29Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 18, "rating_method": "sequential_elo", "raw_elo": 1520.7807241906676, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.933996869115965, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 61.71645590010924, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 2, "attempted_matches": 96, "capped_draws": 8, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 48, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T10:19:17Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 96, "rating_method": "sequential_elo", "raw_elo": 1491.4955399082585, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.58016839641555, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 27.72324997517388, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugins": 1, "attempted_matches": 18, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 9, "draws": 27, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T08:02:37Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 18, "rating_method": "sequential_elo", "raw_elo": 1498.0276047760062, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.31105096947438, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 52.64737393979195, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 3, "attempted_matches": 124, "capped_draws": 6, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 62, "draws": 46, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 44, "max_score": null, "measured_at": "2026-07-27T11:48:17Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 124, "rating_method": "sequential_elo", "raw_elo": 1478.826703359781, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.66259225389678, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 33.435575077886185, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugins": 1, "attempted_matches": 22, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 11, "draws": 17, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-27T10:19:02Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 21, "rating_method": "sequential_elo", "raw_elo": 1488.8943604301728, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.83067183067213, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 59.5501790889026, "unilateral_faults": 1, "wins": 11 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 7, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 14, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T10:18:52Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1458.1644256131383, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 38.52438727472494, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 23, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-26T02:18:23Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1445.4058897559369, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.88422783559002, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 3, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 13, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T10:19:15Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1425.7024844756863, "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-nano", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 33.451022699687655, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 23, "draws": 17, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T10:19:17Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1409.5840570079213, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.519421112195783, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 9 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-27T11:22:49Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1821.193278726695, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugins": 2, "attempted_matches": 80, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 40, "draws": 20, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-26T05:19:00Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1697.2745450187056, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 73.42468015070315, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-26T05:17:50Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1669.0314085778646, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 68.61993149054801, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 26, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-27T11:22:41Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1653.7320041970793, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 66.45071005956129, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 27, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T10:35:48Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1617.3769690127422, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 60.360340816834494, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 28 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 30, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:09:56Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1579.7087489959974, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.71452593995635, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 27, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T10:30:15Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1560.7829388596697, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.305404528632984, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 19 }, { "admitted_plugins": 3, "attempted_matches": 94, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 47, "draws": 77, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 41, "max_score": null, "measured_at": "2026-07-27T11:22:46Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 94, "rating_method": "sequential_elo", "raw_elo": 1567.101366482504, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 46.192829786225445, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 42.49878111612754, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 43, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T10:29:48Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1533.6717755962163, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.23945167121127, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 11 }, { "admitted_plugins": 1, "attempted_matches": 60, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 30, "draws": 33, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:22:46Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 60, "rating_method": "sequential_elo", "raw_elo": 1515.0969212350349, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.376003042374144, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 12 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 19, "draws": 28, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T08:45:33Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1495.7904116780787, "reasoning_level": "Highest", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": null, "requested_effort": "highest", "source": "retained_generation_evidence", "track_id": "full_freedom/intensive" }, "provider_route": "openrouter", "provider_setting_label": "Highest", "reasoning_bracket": "intensive", "reasoning_bucket": "intensive", "reasoning_bucket_label": "Highest", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.97295544313002, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 2, "attempted_matches": 130, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 65, "draws": 82, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:22:49Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 130, "rating_method": "sequential_elo", "raw_elo": 1476.49235088285, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.882383562863147, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 19.03477987847802, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 36, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-27T11:10:04Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1477.865432695363, "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-mini", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.60740336660926, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 40, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-27T11:07:51Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1470.1339268004403, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.738052083219, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 11 }, { "admitted_plugins": 1, "attempted_matches": 28, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 14, "draws": 43, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-27T11:17:55Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 28, "rating_method": "sequential_elo", "raw_elo": 1487.016124867033, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.918714793887677, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 50.78635697673178, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 36, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T11:10:06Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1478.6670650224664, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.9194705568705, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 46.62023516889464, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 2, "attempted_matches": 122, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 61, "draws": 41, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 43, "max_score": null, "measured_at": "2026-07-27T11:18:04Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 122, "rating_method": "sequential_elo", "raw_elo": 1454.7985958238055, "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-nano", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.422092307108727, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 19.9056700157024, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugins": 1, "attempted_matches": 18, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 9, "draws": 35, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T10:43:42Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 18, "rating_method": "sequential_elo", "raw_elo": 1481.8316556844986, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.144079418299455, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 61.71645590010924, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 54, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-26T02:19:07Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1455.7847295731035, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.31872041058993, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 50, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:10:06Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1460.9657967166772, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.70397009886288, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 44.67073949561819, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 48, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 24, "draws": 22, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T10:34:01Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 48, "rating_method": "sequential_elo", "raw_elo": 1440.733349521438, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 23.38150584800255, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 3, "attempted_matches": 78, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 39, "draws": 106, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 52, "max_score": null, "measured_at": "2026-07-27T11:17:57Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 78, "rating_method": "sequential_elo", "raw_elo": 1453.637313690273, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.814064655201765, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 47.36918912473109, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 1, "attempted_matches": 32, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 16, "draws": 16, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:17:57Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1434.7932372194414, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 18.677722595601647, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 49.76941398892446, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 18, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 9, "draws": 36, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T00:21:27Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 18, "rating_method": "sequential_elo", "raw_elo": 1439.8902675454406, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 18.058264435137527, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 60.027768011903404, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T11:30:34Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1931.051509970191, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 96.73066798261004, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 60 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T11:30:33Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1895.2246300132751, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 92.451262399467, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 56 }, { "admitted_plugins": 2, "attempted_matches": 80, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 40, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 12, "max_score": null, "measured_at": "2026-07-26T05:19:29Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1855.4153070757852, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 86.16060543308876, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 68 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:30:30Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1819.332270454036, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 83.56050300184323, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 53 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 2, "max_score": null, "measured_at": "2026-07-26T05:11:53Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1805.431754344661, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 80.36582674270291, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 40 }, { "admitted_plugins": 1, "attempted_matches": 72, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 36, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T11:37:20Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 72, "rating_method": "sequential_elo", "raw_elo": 1758.883007674556, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 76.49983872640665, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 49 }, { "admitted_plugins": 1, "attempted_matches": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 38, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:30:26Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1721.279849578368, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 72.15544813911, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 55 }, { "admitted_plugins": 2, "attempted_matches": 134, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 67, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 58, "max_score": null, "measured_at": "2026-07-27T11:26:08Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 133, "rating_method": "sequential_elo", "raw_elo": 1619.6763359283814, "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-nano", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 59.64569065882853, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 17.139398880661957, "unilateral_faults": 1, "wins": 75 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T11:26:07Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1616.3524860198763, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 59.31522058212656, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 43 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T11:30:33Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1602.9531724861602, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.71385221064524, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 37.38178527761111, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T10:38:17Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1575.875340508706, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 54.39513803855472, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 35 }, { "admitted_plugins": 1, "attempted_matches": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 38, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T11:37:20Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1549.2728597100909, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.609766414462925, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 38 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 23, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T11:37:21Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1559.2077630285237, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 50.46607244200722, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 37.61757338116737, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 35, "max_score": null, "measured_at": "2026-07-27T11:26:11Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1538.3667950040874, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.82574174672981, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 29 }, { "admitted_plugins": 2, "attempted_matches": 86, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 43, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 68, "max_score": null, "measured_at": "2026-07-27T11:30:33Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 86, "rating_method": "sequential_elo", "raw_elo": 1539.8264900054382, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.07016550643658, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 38.46393572312315, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 3, "attempted_matches": 210, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 105, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 110, "max_score": null, "measured_at": "2026-07-27T11:26:10Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 210, "rating_method": "sequential_elo", "raw_elo": 1519.457026192892, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.81950080868389, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 15.625289791427727, "unilateral_faults": 0, "wins": 100 }, { "admitted_plugins": 2, "attempted_matches": 98, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 49, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 71, "max_score": null, "measured_at": "2026-07-27T11:30:26Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 97, "rating_method": "sequential_elo", "raw_elo": 1521.802394121089, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 45.85469736568789, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 39.11849350131416, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 2, "attempted_matches": 144, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 72, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 77, "max_score": null, "measured_at": "2026-07-27T11:26:06Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 144, "rating_method": "sequential_elo", "raw_elo": 1493.3191497437815, "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-mini", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.753682456063075, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 15.036461425079892, "unilateral_faults": 0, "wins": 67 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T11:37:19Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1512.4648061510393, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.05482259085901, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 46.28203845127178, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 23, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T11:30:34Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1489.950348493604, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.19349702401932, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 37.61757338116737, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 35, "max_score": null, "measured_at": "2026-07-27T11:37:19Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1479.067627271918, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.40736615648161, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 42.70587299553475, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 2, "attempted_matches": 140, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 70, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 86, "max_score": null, "measured_at": "2026-07-27T11:37:21Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 140, "rating_method": "sequential_elo", "raw_elo": 1421.697875125174, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.14594446663055, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 54 }, { "admitted_plugins": 2, "attempted_matches": 76, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 38, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 87, "max_score": null, "measured_at": "2026-07-27T11:30:33Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 76, "rating_method": "sequential_elo", "raw_elo": 1407.281846728603, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.89087169341551, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 42.09800666196841, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-26T01:24:23Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1388.981231901262, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.446555315679618, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 52, "max_score": null, "measured_at": "2026-07-26T02:19:03Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1345.5426876668148, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.25796091549614, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 54, "max_score": null, "measured_at": "2026-07-27T11:30:30Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1280.5829410962074, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 16.976547721664623, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 39.80145244019624, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 54, "max_score": null, "measured_at": "2026-07-27T11:30:34Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1268.9210216510749, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 15.144663326584237, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 44.39456088374059, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 3, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 7, "max_score": null, "measured_at": "2026-07-26T05:19:08Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1791.7075385947503, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 89.93824120320421, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 74 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 8, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T11:53:35Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1777.2678447386463, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 88.95151331383552, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 7, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T11:37:21Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1710.4157199319804, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 80.58681788029159, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 37 }, { "admitted_plugins": 1, "attempted_matches": 58, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 29, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 11, "max_score": null, "measured_at": "2026-07-27T11:46:35Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1703.812816431412, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 79.37424207225958, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 38 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 3, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 16, "max_score": null, "measured_at": "2026-07-27T11:46:32Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1701.9160659633524, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 78.99935188287517, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 5, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:46:17Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1691.0689393099397, "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-nano", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 77.54832249268348, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:45:56Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1674.4080128967423, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 75.31957614668558, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 1, "attempted_matches": 56, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 28, "draws": 13, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:37:21Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 56, "rating_method": "sequential_elo", "raw_elo": 1674.3560486853933, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 75.31262484978316, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 78, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 39, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 29, "max_score": null, "measured_at": "2026-07-27T11:53:51Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 78, "rating_method": "sequential_elo", "raw_elo": 1632.355051545612, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 70.76130982029495, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 49 }, { "admitted_plugins": 2, "attempted_matches": 72, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 36, "draws": 12, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 35, "max_score": null, "measured_at": "2026-07-27T11:46:19Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 72, "rating_method": "sequential_elo", "raw_elo": 1644.4298779060618, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 69.03024505442248, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 43.7735813706023, "unilateral_faults": 0, "wins": 81 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 17, "max_score": null, "measured_at": "2026-07-27T11:37:08Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1623.151639774578, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 68.3352570412757, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 8, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 19, "max_score": null, "measured_at": "2026-07-27T11:53:34Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1625.9638890170804, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 66.37931618441283, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 45.462269258808135, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugins": 1, "attempted_matches": 42, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 21, "draws": 5, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T11:53:48Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1589.6396414098424, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 62.019294143192774, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 40.79847712741413, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 27, "draws": 3, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-27T11:46:17Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1579.6136430974516, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 60.76783956869306, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 39.95999312316211, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugins": 2, "attempted_matches": 118, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 59, "draws": 8, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 55, "max_score": null, "measured_at": "2026-07-27T11:46:33Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 118, "rating_method": "sequential_elo", "raw_elo": 1538.1474467950384, "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-mini", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.264851725461014, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 20.8603483440617, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 4, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 16, "max_score": null, "measured_at": "2026-07-26T01:20:52Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1536.7350100578335, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.633695043376434, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 3, "attempted_matches": 138, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 69, "draws": 13, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 107, "max_score": null, "measured_at": "2026-07-27T11:53:35Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 138, "rating_method": "sequential_elo", "raw_elo": 1536.0930490675153, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.39378555896641, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 35.776224893619634, "unilateral_faults": 0, "wins": 118 }, { "admitted_plugins": 1, "attempted_matches": 82, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 41, "draws": 10, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-27T11:46:35Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 82, "rating_method": "sequential_elo", "raw_elo": 1510.098396671887, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 54.55378800839192, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 39 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-26T04:34:09Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1523.1683060416635, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.91719217050105, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 33.41808305530269, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 6, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T10:38:33Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1502.9248303375296, "reasoning_level": "Highest", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": null, "requested_effort": "highest", "source": "retained_generation_evidence", "track_id": "full_freedom/intensive" }, "provider_route": "openrouter", "provider_setting_label": "Highest", "reasoning_bracket": "intensive", "reasoning_bucket": "intensive", "reasoning_bucket_label": "Highest", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.110878446006915, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 10, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 27, "max_score": null, "measured_at": "2026-07-27T11:37:12Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1486.847787377084, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 48.39619884773006, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 39.60745956276516, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 1, "attempted_matches": 35, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 4, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-27T11:37:14Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 35, "rating_method": "sequential_elo", "raw_elo": 1460.076493018715, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.47139940280178, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 42.817992173360395, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 34, "max_score": null, "measured_at": "2026-07-27T11:53:51Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1417.6969290178033, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 41.325050962101, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T11:46:13Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1424.6190995091226, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 39.445251848942995, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 45.462269258808135, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 2, "attempted_matches": 124, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 62, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 87, "max_score": null, "measured_at": "2026-07-27T11:53:45Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 124, "rating_method": "sequential_elo", "raw_elo": 1334.7200708029854, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 30.214944656619977, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 19.33958883428227, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 1, "attempted_matches": 35, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 18, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 50, "max_score": null, "measured_at": "2026-07-27T11:53:48Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 35, "rating_method": "sequential_elo", "raw_elo": 1346.3039086212673, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.658776025462103, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 39.016413493006, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 45, "max_score": null, "measured_at": "2026-07-27T10:45:10Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1338.0261125347924, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.364274717844992, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 17, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 54, "max_score": null, "measured_at": "2026-07-27T10:45:13Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1332.7686768658657, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.004963816593825, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 37.551153208577354, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 20, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 1, "max_score": null, "measured_at": "2026-07-26T05:16:44Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 40, "rating_method": "sequential_elo", "raw_elo": 1908.3795775583417, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 99.7174091533898, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 6, "max_score": null, "measured_at": "2026-07-27T11:07:53Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1839.8110785855636, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 92.43903356479711, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 58 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-27T11:06:02Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1810.7420076245985, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 88.73890042665397, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 58 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 24, "max_score": null, "measured_at": "2026-07-27T11:03:55Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1690.141060653709, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 72.98349769903467, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 42 }, { "admitted_plugins": 2, "attempted_matches": 126, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 63, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 50, "max_score": null, "measured_at": "2026-07-27T11:04:00Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 126, "rating_method": "sequential_elo", "raw_elo": 1640.1550052348434, "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-mini", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 66.30476749736133, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 18.755723064737715, "unilateral_faults": 0, "wins": 76 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 21, "max_score": null, "measured_at": "2026-07-27T11:04:00Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1626.8615300978795, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 64.05449486122448, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 1, "attempted_matches": 54, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 27, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T10:59:24Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 54, "rating_method": "sequential_elo", "raw_elo": 1620.9004693099198, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 63.275737183469275, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugins": 1, "attempted_matches": 62, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 25, "max_score": null, "measured_at": "2026-07-27T10:53:24Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 62, "rating_method": "sequential_elo", "raw_elo": 1604.4884389644276, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 61.59421983387494, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 37 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 36, "max_score": null, "measured_at": "2026-07-27T11:07:53Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1591.3212202571904, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 60.25603724598094, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 34 }, { "admitted_plugins": 3, "attempted_matches": 118, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 59, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 97, "max_score": null, "measured_at": "2026-07-27T11:03:59Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 118, "rating_method": "sequential_elo", "raw_elo": 1597.4696635584298, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 58.8726488028644, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 36.51120413268083, "unilateral_faults": 0, "wins": 131 }, { "admitted_plugins": 3, "attempted_matches": 214, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 107, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 92, "max_score": null, "measured_at": "2026-07-27T11:07:52Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 214, "rating_method": "sequential_elo", "raw_elo": 1569.051457384776, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 57.37331813393658, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 15.334374414189384, "unilateral_faults": 0, "wins": 122 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 34, "max_score": null, "measured_at": "2026-07-27T10:53:27Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1574.402889663777, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 55.37088757570538, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 41.18336395796551, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugins": 1, "attempted_matches": 78, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 39, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T11:07:55Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 78, "rating_method": "sequential_elo", "raw_elo": 1544.0623728482103, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 54.40449302982698, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 50 }, { "admitted_plugins": 3, "attempted_matches": 140, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 70, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 109, "max_score": null, "measured_at": "2026-07-27T11:54:18Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 140, "rating_method": "sequential_elo", "raw_elo": 1552.2221681288854, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 53.439927382671186, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 31.933316946790622, "unilateral_faults": 0, "wins": 149 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 23, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 38, "max_score": null, "measured_at": "2026-07-27T11:54:22Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1544.5012678250691, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 52.23449928003549, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 33.815994700812965, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugins": 2, "attempted_matches": 124, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 62, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 62, "max_score": null, "measured_at": "2026-07-27T10:59:20Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 124, "rating_method": "sequential_elo", "raw_elo": 1514.7809634969965, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 49.87227457080003, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 19.267903630526114, "unilateral_faults": 0, "wins": 62 }, { "admitted_plugins": 2, "attempted_matches": 128, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 64, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 71, "max_score": null, "measured_at": "2026-07-27T11:06:05Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 128, "rating_method": "sequential_elo", "raw_elo": 1494.0376407858523, "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-nano", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 47.26461648443617, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 18.289400506511907, "unilateral_faults": 0, "wins": 57 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 45, "max_score": null, "measured_at": "2026-07-26T02:17:20Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1488.6688151212495, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 44.886064479879934, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 50, "max_score": null, "measured_at": "2026-07-27T11:03:53Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1433.6870639522708, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 37.38497422902105, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 37.38178527761111, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 39, "max_score": null, "measured_at": "2026-07-27T10:59:17Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1412.1255644657329, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 36.6633342427911, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 27 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 40, "max_score": null, "measured_at": "2026-07-27T11:06:04Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1422.872779287951, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.574874573353014, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 41.18336395796551, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 40, "max_score": null, "measured_at": "2026-07-27T11:03:58Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1419.3250538494135, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.57852104475718, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 46.28203845127178, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 27, "max_score": null, "measured_at": "2026-07-26T02:15:57Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1392.94803374959, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 32.381026187959016, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 43, "max_score": null, "measured_at": "2026-07-27T11:06:06Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1379.5223503800132, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 29.91154038722549, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 41.18336395796551, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 47, "max_score": null, "measured_at": "2026-07-27T11:07:52Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1370.1870771688791, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 28.69197294013675, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 41.18336395796551, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 59, "max_score": null, "measured_at": "2026-07-27T11:07:55Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1262.971405382954, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 14.82966031579288, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 39.80145244019624, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 1, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 4, "max_score": null, "measured_at": "2026-07-27T11:07:56Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1910.1404215986424, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 61 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 9, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 16, "max_score": null, "measured_at": "2026-07-27T11:06:02Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1686.9133200163933, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 65.52897413963234, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 43 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 20, "max_score": null, "measured_at": "2026-07-27T11:03:50Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1683.6684140637717, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 64.91576179922941, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 46 }, { "admitted_plugins": 3, "attempted_matches": 114, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 6, "distinct_rated_opponents": 57, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 55, "max_score": null, "measured_at": "2026-07-27T11:07:56Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 114, "rating_method": "sequential_elo", "raw_elo": 1692.99759374344, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 63.7778049142926, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 38.178218158143345, "unilateral_faults": 0, "wins": 165 }, { "admitted_plugins": 2, "attempted_matches": 80, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 40, "draws": 0, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-26T05:18:46Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 80, "rating_method": "sequential_elo", "raw_elo": 1686.0665086802464, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 63.18013490216033, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 54 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 2, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 30, "max_score": null, "measured_at": "2026-07-27T11:03:56Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1611.591302525787, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 51.26533615379074, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 37.38178527761111, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 5, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 5, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T10:59:36Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1548.0692879399865, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 43.793641641644086, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 31 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 9, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 9, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 31, "max_score": null, "measured_at": "2026-07-27T08:14:34Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1541.4118035776828, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.877873486874975, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 26 }, { "admitted_plugins": 3, "attempted_matches": 212, "capped_draws": 103, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 106, "draws": 103, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 44, "max_score": null, "measured_at": "2026-07-27T11:07:56Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 212, "rating_method": "sequential_elo", "raw_elo": 1537.8079299083918, "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-nano", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 42.56690883616381, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 15.33901212384661, "unilateral_faults": 0, "wins": 65 }, { "admitted_plugins": 1, "attempted_matches": 68, "capped_draws": 15, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 34, "draws": 15, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 28, "max_score": null, "measured_at": "2026-07-27T09:17:43Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 68, "rating_method": "sequential_elo", "raw_elo": 1524.6754320667146, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 40.39565736475438, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 25 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 38, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-26T05:18:58Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1506.0213602790975, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 35.50824142419229, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 32.561240097148016, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 2, "attempted_matches": 144, "capped_draws": 52, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 72, "draws": 52, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 50, "max_score": null, "measured_at": "2026-07-27T10:59:27Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 144, "rating_method": "sequential_elo", "raw_elo": 1488.5751193579963, "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-mini", "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 34.97743293260359, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 15.036461425079892, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugins": 1, "attempted_matches": 78, "capped_draws": 42, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 39, "draws": 42, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 26, "max_score": null, "measured_at": "2026-07-27T10:59:32Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 78, "rating_method": "sequential_elo", "raw_elo": 1466.4677843586585, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.86645017234374, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 10 }, { "admitted_plugins": 3, "attempted_matches": 198, "capped_draws": 88, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 99, "draws": 88, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 67, "max_score": null, "measured_at": "2026-07-27T11:06:04Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 198, "rating_method": "sequential_elo", "raw_elo": 1467.3701302724855, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 31.39612230112461, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 17.42733990918024, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugins": 1, "attempted_matches": 70, "capped_draws": 54, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 35, "draws": 54, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T10:53:26Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 70, "rating_method": "sequential_elo", "raw_elo": 1442.2170907590032, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 27.727323840541924, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 6 }, { "admitted_plugins": 1, "attempted_matches": 46, "capped_draws": 9, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 23, "draws": 21, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 33, "max_score": null, "measured_at": "2026-07-27T11:04:07Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 46, "rating_method": "sequential_elo", "raw_elo": 1453.7327498486231, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.952493120378215, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 36.2356618633981, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 1, "attempted_matches": 66, "capped_draws": 48, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 33, "draws": 48, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 14, "max_score": null, "measured_at": "2026-07-27T10:53:26Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 66, "rating_method": "sequential_elo", "raw_elo": 1432.8957272786026, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 26.06694876849134, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 4 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 32, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 22, "draws": 58, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 10, "max_score": null, "measured_at": "2026-07-27T11:03:50Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1447.3687877312982, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.696007242727312, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 38.41912513169022, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 37, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 22, "draws": 37, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 5, "max_score": null, "measured_at": "2026-07-26T21:50:12Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1438.8587143860132, "reasoning_level": "Highest", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": null, "requested_effort": "highest", "source": "retained_generation_evidence", "track_id": "full_freedom/intensive" }, "provider_route": "openrouter", "provider_setting_label": "Highest", "reasoning_bracket": "intensive", "reasoning_bucket": "intensive", "reasoning_bucket_label": "Highest", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": null, "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.32370388835863, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 2, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 0, "draws": 65, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 13, "max_score": null, "measured_at": "2026-07-26T02:17:44Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1441.610914575508, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.309943409461283, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 44, "capped_draws": 28, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 22, "draws": 54, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T10:53:39Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1445.100399542236, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 25.155907260050387, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 39.941634169259466, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 84, "capped_draws": 56, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 42, "draws": 109, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 23, "max_score": null, "measured_at": "2026-07-27T10:59:44Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 84, "rating_method": "sequential_elo", "raw_elo": 1443.6062775081773, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.99822893746736, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 39.34626684974488, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 42, "capped_draws": 27, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 21, "draws": 42, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 15, "max_score": null, "measured_at": "2026-07-27T11:06:04Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 42, "rating_method": "sequential_elo", "raw_elo": 1445.205504297169, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.622792993226422, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 44.37464258315117, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 29, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 69, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 9, "max_score": null, "measured_at": "2026-07-27T10:53:27Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1435.9046812811634, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 24.52349474191262, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 33.54983807626827, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 2, "attempted_matches": 88, "capped_draws": 58, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 44, "draws": 103, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 37, "max_score": null, "measured_at": "2026-07-27T11:05:59Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 88, "rating_method": "sequential_elo", "raw_elo": 1428.1658766468497, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 22.759434959312564, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 38.11029391633042, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 0, "draws": 32, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 8, "max_score": null, "measured_at": "2026-07-26T02:14:59Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1419.7799946445818, "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" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 21.92797491218185, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 38, "capped_draws": 25, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 19, "draws": 54, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 18, "max_score": null, "measured_at": "2026-07-27T10:59:21Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 38, "rating_method": "sequential_elo", "raw_elo": 1400.630372981852, "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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "high" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 18.44050863736999, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3", "track_id": "full_freedom/intensive", "track_name": "Intensive filter", "uncertainty": 38.53975118769762, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 64, "capped_draws": 12, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 32, "draws": 12, "entry_count": null, "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 }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 32, "max_score": null, "measured_at": "2026-07-27T10:53:25Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 64, "rating_method": "sequential_elo", "raw_elo": 1370.0658232755432, "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_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": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "requested_reasoning_effort": "xhigh" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260727-b63faa64fdbb", "row_kind": "game", "score": 16.21797777560009, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_mixed_variants_v9", "snapshot_id": "20260727_140229", "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": 20 } ], "schema_version": 8, "snapshot_id": "20260727_140229", "suite_line_id": "gamebench2", "suite_version": "2-known8-r3" }