{ "benchmark_line": "gamebench2", "comparability_tuples": [ { "evaluation_family": "codegen_public_benchmark", "rating_method": "sequential_elo", "reasoning_effort": "highest", "results_cut_id": "20260713_194906", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_kind": "full_freedom" }, { "evaluation_family": "codegen_public_benchmark", "rating_method": "sequential_elo", "reasoning_effort": "medium", "results_cut_id": "20260713_194906", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_kind": "full_freedom" }, { "evaluation_family": "codegen_public_benchmark", "rating_method": "sequential_elo", "reasoning_effort": "mixed", "results_cut_id": "20260713_194906", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_kind": "full_freedom" }, { "evaluation_family": "codegen_public_benchmark", "rating_method": "sequential_elo", "reasoning_effort": "none", "results_cut_id": "20260713_194906", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_kind": "full_freedom" }, { "evaluation_family": "codegen_public_benchmark", "rating_method": "sequential_elo", "reasoning_effort": "aggregate", "results_cut_id": "20260713_194906", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "overall", "track_kind": "overall" } ], "generated_at": "2026-07-13T19:49:06Z", "public_release_id": "gb2-20260713-37697e440dc9", "results_cut_id": "gb2-20260713-37697e440dc9", "rows": [ { "admitted_plugins": 8, "attempted_matches": 1251, "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-2026-07-12": 11 }, "run_count": 8, "token_priced_attempt_count": 11, "total": 12.66097 }, "codegen_evaluated_cells": 8, "conditional_success_score": 73.67927701948544, "contributing_entrants": null, "distinct_rated_opponents": 626, "draws": 100, "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": "2026-07-13T11:18:24Z", "losses": 84, "max_score": 100.0, "measured_at": null, "min_score": 0.0, "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": 1245, "rating_method": "sequential_elo", "raw_elo": 1895.9212662848677, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 73.67927701948544, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 6, "wins": 1061 }, { "admitted_plugins": 8, "attempted_matches": 1273, "capped_draws": 25, "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-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 80.47395 }, "codegen_evaluated_cells": 8, "conditional_success_score": 72.38492380259433, "contributing_entrants": null, "distinct_rated_opponents": 636, "draws": 117, "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": "2026-07-13T11:17:54Z", "losses": 232, "max_score": 100.0, "measured_at": null, "min_score": 3.7904762066821025, "model_code_failure_rate": 0.0, "model_code_failures": 0, "model_display_name": "GPT-5.6 Sol", "model_slug": "gpt-5-6-sol", "plugin_success_rate": 1.0, "provider": "OpenAI", "provider_key": "openai", "rank": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1260, "rating_method": "sequential_elo", "raw_elo": 1780.9955276529745, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 72.38492380259433, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 1, "wins": 911 }, { "admitted_plugins": 7, "attempted_matches": 1245, "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-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 4.0372 }, "codegen_evaluated_cells": 8, "conditional_success_score": 72.21883276340077, "contributing_entrants": null, "distinct_rated_opponents": 621, "draws": 170, "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": "2026-07-13T11:16:50Z", "losses": 128, "max_score": 86.59651961160996, "measured_at": null, "min_score": 42.101358265742746, "model_code_failure_rate": 0.125, "model_code_failures": 1, "model_display_name": "Claude Fable 5", "model_slug": "claude-fable-5", "plugin_success_rate": 0.875, "provider": "Anthropic", "provider_key": "anthropic", "rank": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1239, "rating_method": "sequential_elo", "raw_elo": 1859.9976797834684, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 69.84775922173306, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 941 }, { "admitted_plugins": 7, "attempted_matches": 1245, "capped_draws": 21, "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-2026-07-12": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 7.44989 }, "codegen_evaluated_cells": 8, "conditional_success_score": 70.89694035940671, "contributing_entrants": null, "distinct_rated_opponents": 626, "draws": 156, "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": "2026-07-13T11:18:43Z", "losses": 173, "max_score": 90.52286342805895, "measured_at": null, "min_score": 51.90054642237549, "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1245, "rating_method": "sequential_elo", "raw_elo": 1827.9186952521943, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 68.56926691137262, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 916 }, { "admitted_plugins": 7, "attempted_matches": 1131, "capped_draws": 104, "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-2026-07-12": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 21.885475 }, "codegen_evaluated_cells": 8, "conditional_success_score": 69.89301893844359, "contributing_entrants": null, "distinct_rated_opponents": 570, "draws": 237, "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": "2026-07-13T11:18:50Z", "losses": 117, "max_score": 99.70622072012152, "measured_at": null, "min_score": 7.861489901697698, "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": 1118, "rating_method": "sequential_elo", "raw_elo": 1804.4068332428672, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 67.5983060275447, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 764 }, { "admitted_plugins": 8, "attempted_matches": 1271, "capped_draws": 36, "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-2026-07-12": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 21.140645 }, "codegen_evaluated_cells": 8, "conditional_success_score": 66.72404359849178, "contributing_entrants": null, "distinct_rated_opponents": 636, "draws": 232, "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": "2026-07-13T11:18:53Z", "losses": 79, "max_score": 100.0, "measured_at": null, "min_score": 20.816680906992, "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1256, "rating_method": "sequential_elo", "raw_elo": 1865.1994334603448, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 66.72404359849178, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 3, "wins": 945 }, { "admitted_plugins": 8, "attempted_matches": 1247, "capped_draws": 9, "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-2026-07-12": 10 }, "run_count": 9, "token_priced_attempt_count": 10, "total": 28.806541000000003 }, "codegen_evaluated_cells": 9, "conditional_success_score": 56.611113304620986, "contributing_entrants": null, "distinct_rated_opponents": 623, "draws": 273, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:17:34Z", "losses": 197, "max_score": 86.16311739565705, "measured_at": null, "min_score": 9.920800162399148, "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": 1242, "rating_method": "sequential_elo", "raw_elo": 1711.7948492624607, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 1, "repaired_rate": 0.1111111111111111, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 54.96845939316894, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 3, "wins": 772 }, { "admitted_plugins": 8, "attempted_matches": 1248, "capped_draws": 18, "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-2026-07-12": 10 }, "run_count": 9, "token_priced_attempt_count": 10, "total": 4.1199200000000005 }, "codegen_evaluated_cells": 9, "conditional_success_score": 55.49385388463494, "contributing_entrants": null, "distinct_rated_opponents": 623, "draws": 244, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T18:48:15Z", "losses": 172, "max_score": 80.83653200086476, "measured_at": null, "min_score": 25.03713437216872, "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1242, "rating_method": "sequential_elo", "raw_elo": 1763.3361589483193, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.1111111111111111, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 53.8836188826375, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 3, "wins": 826 }, { "admitted_plugins": 8, "attempted_matches": 1248, "capped_draws": 70, "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-2026-07-12": 11 }, "run_count": 8, "token_priced_attempt_count": 11, "total": 65.3280125 }, "codegen_evaluated_cells": 8, "conditional_success_score": 51.831196830812125, "contributing_entrants": null, "distinct_rated_opponents": 625, "draws": 282, "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": "2026-07-13T16:11:38Z", "losses": 228, "max_score": 79.72411496155975, "measured_at": null, "min_score": 28.075303957431895, "model_code_failure_rate": 0.0, "model_code_failures": 0, "model_display_name": "GPT-5.6 Terra", "model_slug": "gpt-5-6-terra", "plugin_success_rate": 1.0, "provider": "OpenAI", "provider_key": "openai", "rank": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1244, "rating_method": "sequential_elo", "raw_elo": 1665.4419312545167, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 51.831196830812125, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 3, "wins": 734 }, { "admitted_plugins": 8, "attempted_matches": 1264, "capped_draws": 126, "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": 50.26404387209092, "contributing_entrants": null, "distinct_rated_opponents": 625, "draws": 374, "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": "2026-07-13T19:18:02Z", "losses": 265, "max_score": 92.37554944921584, "measured_at": null, "min_score": 15.52961769268853, "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1243, "rating_method": "sequential_elo", "raw_elo": 1666.234014034844, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 8, "repaired_rate": 1.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 50.26404387209092, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 11, "wins": 604 }, { "admitted_plugins": 8, "attempted_matches": 1276, "capped_draws": 125, "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-2026-07-12": 10 }, "run_count": 8, "token_priced_attempt_count": 10, "total": 0.7485199999999999 }, "codegen_evaluated_cells": 8, "conditional_success_score": 49.29725888272484, "contributing_entrants": null, "distinct_rated_opponents": 640, "draws": 415, "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": "2026-07-13T17:37:51Z", "losses": 282, "max_score": 93.92197991363965, "measured_at": null, "min_score": 13.62877706153271, "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1258, "rating_method": "sequential_elo", "raw_elo": 1638.1199975892869, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 49.29725888272484, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 9, "wins": 561 }, { "admitted_plugins": 8, "attempted_matches": 1165, "capped_draws": 64, "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-2026-07-12": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 3.98915 }, "codegen_evaluated_cells": 8, "conditional_success_score": 49.07193775824096, "contributing_entrants": null, "distinct_rated_opponents": 600, "draws": 343, "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": "2026-07-13T11:18:45Z", "losses": 234, "max_score": 100.0, "measured_at": null, "min_score": 14.518901175227816, "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": 1156, "rating_method": "sequential_elo", "raw_elo": 1650.4493101930552, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 49.07193775824096, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 9, "wins": 579 }, { "admitted_plugins": 12, "attempted_matches": 2143, "capped_draws": 152, "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-2026-07-12": 15 }, "run_count": 12, "token_priced_attempt_count": 15, "total": 12.214044 }, "codegen_evaluated_cells": 12, "conditional_success_score": 47.56517919446139, "contributing_entrants": null, "distinct_rated_opponents": 1074, "draws": 575, "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": [ "GB2-03" ], "infra_failures_excluded": 1, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:18:55Z", "losses": 506, "max_score": 83.58987122827983, "measured_at": null, "min_score": 15.497093457640895, "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 2143, "rating_method": "sequential_elo", "raw_elo": 1642.1563896208315, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 2, "repaired_rate": 0.16666666666666666, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 47.56517919446139, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 1062 }, { "admitted_plugins": 8, "attempted_matches": 1266, "capped_draws": 212, "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-2026-07-12": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 3.542855 }, "codegen_evaluated_cells": 8, "conditional_success_score": 47.20981092662286, "contributing_entrants": null, "distinct_rated_opponents": 639, "draws": 444, "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": "2026-07-13T18:28:37Z", "losses": 254, "max_score": 85.91160100452133, "measured_at": null, "min_score": 19.541203899412803, "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1257, "rating_method": "sequential_elo", "raw_elo": 1592.8853853515752, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 47.20981092662286, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 6, "wins": 559 }, { "admitted_plugins": 8, "attempted_matches": 1264, "capped_draws": 111, "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-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 0.97393 }, "codegen_evaluated_cells": 8, "conditional_success_score": 45.948850737620106, "contributing_entrants": null, "distinct_rated_opponents": 634, "draws": 370, "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": "2026-07-13T17:59:25Z", "losses": 343, "max_score": 78.8982296737467, "measured_at": null, "min_score": 9.13197672529834, "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1252, "rating_method": "sequential_elo", "raw_elo": 1584.8470076121366, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 45.948850737620106, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 4, "wins": 539 }, { "admitted_plugins": 15, "attempted_matches": 2513, "capped_draws": 354, "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-2026-07-12": 25 }, "run_count": 17, "token_priced_attempt_count": 25, "total": 5.07700365 }, "codegen_evaluated_cells": 17, "conditional_success_score": 47.00678735360725, "contributing_entrants": null, "distinct_rated_opponents": 1260, "draws": 775, "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": [ "GB2-05" ], "infra_failures_excluded": 1, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:23:24Z", "losses": 726, "max_score": 95.07321615577396, "measured_at": null, "min_score": 11.62667967015868, "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 2508, "rating_method": "sequential_elo", "raw_elo": 1593.3655618002524, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 5, "repaired_rate": 0.29411764705882354, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 45.55868236667957, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 1, "wins": 1007 }, { "admitted_plugins": 8, "attempted_matches": 1260, "capped_draws": 139, "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-2026-07-12": 10 }, "run_count": 8, "token_priced_attempt_count": 10, "total": 2.2561124999999995 }, "codegen_evaluated_cells": 8, "conditional_success_score": 44.44751572350101, "contributing_entrants": null, "distinct_rated_opponents": 635, "draws": 416, "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": "2026-07-13T18:48:15Z", "losses": 291, "max_score": 82.30557434685794, "measured_at": null, "min_score": 14.519546549031492, "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1255, "rating_method": "sequential_elo", "raw_elo": 1594.464728220512, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 44.44751572350101, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 3, "wins": 548 }, { "admitted_plugins": 8, "attempted_matches": 1265, "capped_draws": 139, "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": 0.4567, "mean": 0.3681425, "median": 0.355077, "min": 0.234622, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 2.945139999999999 }, "codegen_evaluated_cells": 8, "conditional_success_score": 43.91806233006658, "contributing_entrants": null, "distinct_rated_opponents": 636, "draws": 398, "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": "2026-07-13T14:18:39Z", "losses": 297, "max_score": 70.32957472930792, "measured_at": null, "min_score": 20.849828926322857, "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1254, "rating_method": "sequential_elo", "raw_elo": 1592.1540012263274, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 43.91806233006658, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 5, "wins": 559 }, { "admitted_plugins": 7, "attempted_matches": 1241, "capped_draws": 35, "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-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 1.262825 }, "codegen_evaluated_cells": 8, "conditional_success_score": 44.78300955956154, "contributing_entrants": null, "distinct_rated_opponents": 622, "draws": 303, "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": "2026-07-13T11:07:15Z", "losses": 394, "max_score": 80.92699793368016, "measured_at": null, "min_score": 10.536099280916575, "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": 1241, "rating_method": "sequential_elo", "raw_elo": 1584.8108268945598, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 43.312703200127544, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 544 }, { "admitted_plugins": 6, "attempted_matches": 1080, "capped_draws": 135, "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-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 0.390976 }, "codegen_evaluated_cells": 8, "conditional_success_score": 45.90073295157999, "contributing_entrants": null, "distinct_rated_opponents": 541, "draws": 275, "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": "2026-07-13T11:17:56Z", "losses": 344, "max_score": 71.26903378287814, "measured_at": null, "min_score": 21.69121170153766, "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1078, "rating_method": "sequential_elo", "raw_elo": 1573.8300265086018, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 42.715445121088194, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 1, "wins": 459 }, { "admitted_plugins": 7, "attempted_matches": 1243, "capped_draws": 67, "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": 0.3825, "mean": 0.27230375, "median": 0.25636749999999997, "min": 0.236235, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 2.17843 }, "codegen_evaluated_cells": 8, "conditional_success_score": 43.846531385589635, "contributing_entrants": null, "distinct_rated_opponents": 623, "draws": 349, "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": "2026-07-13T11:16:56Z", "losses": 363, "max_score": 71.27763820744504, "measured_at": null, "min_score": 13.244643810555974, "model_code_failure_rate": 0.125, "model_code_failures": 1, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": 0.875, "provider": "Anthropic", "provider_key": "anthropic", "rank": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1243, "rating_method": "sequential_elo", "raw_elo": 1582.3827248107011, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 42.40697128077773, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 531 }, { "admitted_plugins": 6, "attempted_matches": 1076, "capped_draws": 156, "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": 45.42604803979628, "contributing_entrants": null, "distinct_rated_opponents": 538, "draws": 265, "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": "2026-07-13T11:17:33Z", "losses": 341, "max_score": 85.67465290743922, "measured_at": null, "min_score": 15.029053862157538, "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1075, "rating_method": "sequential_elo", "raw_elo": 1574.876009512716, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 42.273701035639824, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 469 }, { "admitted_plugins": 8, "attempted_matches": 1256, "capped_draws": 161, "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-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 1.743525 }, "codegen_evaluated_cells": 8, "conditional_success_score": 41.46092745060459, "contributing_entrants": null, "distinct_rated_opponents": 626, "draws": 448, "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": "2026-07-13T15:25:01Z", "losses": 284, "max_score": 91.70584983423836, "measured_at": null, "min_score": 8.792181774741303, "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1246, "rating_method": "sequential_elo", "raw_elo": 1596.5152268113138, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 41.46092745060459, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 5, "wins": 514 }, { "admitted_plugins": 6, "attempted_matches": 898, "capped_draws": 128, "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": 43.54352147792685, "contributing_entrants": null, "distinct_rated_opponents": 449, "draws": 244, "entry_count": 6, "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": "2026-07-13T11:18:03Z", "losses": 380, "max_score": 70.89086607159972, "measured_at": null, "min_score": 13.264083848544765, "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 898, "rating_method": "sequential_elo", "raw_elo": 1538.154704225489, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 40.521812669775365, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 449 }, { "admitted_plugins": 7, "attempted_matches": 1125, "capped_draws": 142, "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-2026-07-12": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 1.42050125 }, "codegen_evaluated_cells": 8, "conditional_success_score": 41.53044627492922, "contributing_entrants": null, "distinct_rated_opponents": 571, "draws": 270, "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": "2026-07-13T11:18:07Z", "losses": 422, "max_score": 68.10303654582466, "measured_at": null, "min_score": 15.984096147083603, "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1122, "rating_method": "sequential_elo", "raw_elo": 1503.3040011074634, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 40.16692738978267, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 430 }, { "admitted_plugins": 6, "attempted_matches": 1076, "capped_draws": 176, "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": 42.54064538804611, "contributing_entrants": null, "distinct_rated_opponents": 538, "draws": 338, "entry_count": 6, "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": "2026-07-13T11:16:59Z", "losses": 328, "max_score": 81.88087560362533, "measured_at": null, "min_score": 13.009111045617562, "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1076, "rating_method": "sequential_elo", "raw_elo": 1547.107092405945, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 39.58853130745503, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 410 }, { "admitted_plugins": 6, "attempted_matches": 1067, "capped_draws": 24, "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": 42.10767006502641, "contributing_entrants": null, "distinct_rated_opponents": 534, "draws": 281, "entry_count": 6, "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": "2026-07-13T10:53:23Z", "losses": 315, "max_score": 59.58264825078116, "measured_at": null, "min_score": 12.540709613495318, "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1066, "rating_method": "sequential_elo", "raw_elo": 1585.212525423465, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 39.1856023679816, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 470 }, { "admitted_plugins": 8, "attempted_matches": 1269, "capped_draws": 159, "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": 0.07806, "mean": 0.06121625, "median": 0.061152, "min": 0.049788, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 0.4897299999999999 }, "codegen_evaluated_cells": 8, "conditional_success_score": 38.947734987153694, "contributing_entrants": null, "distinct_rated_opponents": 630, "draws": 445, "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": "2026-07-13T19:18:02Z", "losses": 362, "max_score": 62.65785807563824, "measured_at": null, "min_score": 11.421558133782472, "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": 1251, "rating_method": "sequential_elo", "raw_elo": 1534.219935928596, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 38.947734987153694, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 5, "wins": 444 }, { "admitted_plugins": 6, "attempted_matches": 914, "capped_draws": 105, "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": 41.71617219774557, "contributing_entrants": null, "distinct_rated_opponents": 454, "draws": 170, "entry_count": 6, "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": "2026-07-13T18:14:57Z", "losses": 291, "max_score": 88.59703072475118, "measured_at": null, "min_score": 5.510322141763682, "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 903, "rating_method": "sequential_elo", "raw_elo": 1590.1553819546968, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 38.82127255036194, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 10, "wins": 442 }, { "admitted_plugins": 6, "attempted_matches": 925, "capped_draws": 57, "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": 41.2811008153348, "contributing_entrants": null, "distinct_rated_opponents": 464, "draws": 210, "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": "2026-07-13T19:18:02Z", "losses": 358, "max_score": 60.293433204479186, "measured_at": null, "min_score": 12.76276880459896, "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 914, "rating_method": "sequential_elo", "raw_elo": 1528.6435719264146, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 38.41639300783421, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 4, "wins": 346 }, { "admitted_plugins": 8, "attempted_matches": 1271, "capped_draws": 156, "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-2026-07-12": 11 }, "run_count": 8, "token_priced_attempt_count": 11, "total": 1.33952 }, "codegen_evaluated_cells": 8, "conditional_success_score": 37.8447761314094, "contributing_entrants": null, "distinct_rated_opponents": 636, "draws": 459, "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": "2026-07-13T15:06:27Z", "losses": 344, "max_score": 66.27290316140129, "measured_at": null, "min_score": 10.94878978246065, "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1259, "rating_method": "sequential_elo", "raw_elo": 1518.2704342333318, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 37.8447761314094, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 3, "wins": 456 }, { "admitted_plugins": 7, "attempted_matches": 1092, "capped_draws": 203, "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": 38.62543981510385, "contributing_entrants": null, "distinct_rated_opponents": 550, "draws": 368, "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": "2026-07-13T11:13:38Z", "losses": 358, "max_score": 75.9025597410182, "measured_at": null, "min_score": 10.124210580685428, "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1078, "rating_method": "sequential_elo", "raw_elo": 1491.0037867490844, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 37.35729749160615, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 7, "wins": 352 }, { "admitted_plugins": 8, "attempted_matches": 1168, "capped_draws": 169, "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": 0.309345, "mean": 0.239705, "median": 0.232815, "min": 0.175235, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 1.91764 }, "codegen_evaluated_cells": 8, "conditional_success_score": 37.21615883516933, "contributing_entrants": null, "distinct_rated_opponents": 588, "draws": 377, "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": "2026-07-13T17:37:51Z", "losses": 342, "max_score": 59.526947576565824, "measured_at": null, "min_score": 14.877885447048715, "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1143, "rating_method": "sequential_elo", "raw_elo": 1526.0021889372078, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 37.21615883516933, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 16, "wins": 424 }, { "admitted_plugins": 8, "attempted_matches": 1251, "capped_draws": 73, "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-2026-07-12": 9 }, "run_count": 9, "token_priced_attempt_count": 9, "total": 1.069485 }, "codegen_evaluated_cells": 9, "conditional_success_score": 38.30307049865906, "contributing_entrants": null, "distinct_rated_opponents": 621, "draws": 333, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:18:17Z", "losses": 377, "max_score": 61.59221622927624, "measured_at": null, "min_score": 12.279638610710084, "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1239, "rating_method": "sequential_elo", "raw_elo": 1538.9197284923318, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 37.191651116449, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 4, "wins": 529 }, { "admitted_plugins": 18, "attempted_matches": 3070, "capped_draws": 400, "codegen_cost_usd": { "admitted_cell_count": 18, "cell_count": 8, "cost_basis_counts": { "provider_reported": 55 }, "evidence_basis": "Provider-reported", "failed_cell_count": 7, "max": 0.25823185294999995, "mean": 0.20731004458333335, "median": 0.20662718916666667, "min": 0.13654539825, "recorded_attempt_count": 55, "run_count": 25, "total": 5.1714206112 }, "codegen_evaluated_cells": 25, "conditional_success_score": 40.104186114581104, "contributing_entrants": null, "distinct_rated_opponents": 1537, "draws": 1042, "entry_count": 18, "failed_game_aliases": [ "GB2-01", "GB2-03", "GB2-04", "GB2-06" ], "first_pass_admitted": 1, "first_pass_rate": 0.04, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_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": "2026-07-13T11:18:54Z", "losses": 826, "max_score": 64.94690677132208, "measured_at": null, "min_score": 10.660343551755462, "model_code_failure_rate": 0.28, "model_code_failures": 7, "model_display_name": "GLM-5.2", "model_slug": "z-ai-glm-5-2", "plugin_success_rate": 0.72, "provider": "Zhipu", "provider_key": "z-ai", "rank": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 3046, "rating_method": "sequential_elo", "raw_elo": 1561.584504103287, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 17, "repaired_rate": 0.68, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 36.94220646382741, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 4, "wins": 1178 }, { "admitted_plugins": 16, "attempted_matches": 2233, "capped_draws": 373, "codegen_cost_usd": { "admitted_cell_count": 16, "cell_count": 8, "cost_basis_counts": { "provider_reported": 52 }, "evidence_basis": "Provider-reported", "failed_cell_count": 8, "max": 0.1697954668, "mean": 0.12351497933333334, "median": 0.12954777533333334, "min": 0.05546312440000001, "recorded_attempt_count": 52, "run_count": 24, "total": 2.964359504 }, "codegen_evaluated_cells": 24, "conditional_success_score": 40.54469529572177, "contributing_entrants": null, "distinct_rated_opponents": 1135, "draws": 690, "entry_count": 16, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "GB2-05", "GB2-06" ], "first_pass_admitted": 3, "first_pass_rate": 0.125, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T19:18:02Z", "losses": 574, "max_score": 63.63124555669186, "measured_at": null, "min_score": 17.458145034751666, "model_code_failure_rate": 0.3333333333333333, "model_code_failures": 8, "model_display_name": "GLM-5.2", "model_slug": "z-ai-glm-5-2", "plugin_success_rate": 0.6666666666666666, "provider": "Zhipu", "provider_key": "z-ai", "rank": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 2192, "rating_method": "sequential_elo", "raw_elo": 1571.3343127420137, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 13, "repaired_rate": 0.5416666666666666, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 36.63626790496484, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 19, "wins": 928 }, { "admitted_plugins": 7, "attempted_matches": 1243, "capped_draws": 166, "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-2026-07-12": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 0.624428 }, "codegen_evaluated_cells": 8, "conditional_success_score": 37.78697868650787, "contributing_entrants": null, "distinct_rated_opponents": 622, "draws": 432, "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": "2026-07-13T11:15:41Z", "losses": 374, "max_score": 64.72154766303917, "measured_at": null, "min_score": 9.95306063713581, "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": 37, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1240, "rating_method": "sequential_elo", "raw_elo": 1523.8821688444857, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 36.54636454259518, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 434 }, { "admitted_plugins": 8, "attempted_matches": 1268, "capped_draws": 130, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 11 }, "evidence_basis": "Standard list-price estimate", "max": 0.094594, "mean": 0.0571955, "median": 0.043012, "min": 0.032534, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 11 }, "run_count": 8, "token_priced_attempt_count": 11, "total": 0.4575640000000001 }, "codegen_evaluated_cells": 8, "conditional_success_score": 36.54444523651211, "contributing_entrants": null, "distinct_rated_opponents": 639, "draws": 416, "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": "2026-07-13T11:07:36Z", "losses": 447, "max_score": 58.420430590270925, "measured_at": null, "min_score": 9.661510668959371, "model_code_failure_rate": 0.0, "model_code_failures": 0, "model_display_name": "GPT 4.1", "model_slug": "gpt-4-1", "plugin_success_rate": 1.0, "provider": "OpenAI", "provider_key": "openai", "rank": 38, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1257, "rating_method": "sequential_elo", "raw_elo": 1487.165424185781, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 36.54444523651211, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 3, "wins": 394 }, { "admitted_plugins": 17, "attempted_matches": 2875, "capped_draws": 340, "codegen_cost_usd": { "admitted_cell_count": 17, "cell_count": 8, "cost_basis_counts": { "provider_reported": 37 }, "evidence_basis": "Provider-reported", "failed_cell_count": 7, "max": 0.005169185000000001, "mean": 0.002871050658333333, "median": 0.0023354879666666667, "min": 0.00169122, "recorded_attempt_count": 37, "run_count": 24, "total": 0.0689052158 }, "codegen_evaluated_cells": 24, "conditional_success_score": 39.74564768749891, "contributing_entrants": null, "distinct_rated_opponents": 1439, "draws": 733, "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": "2026-07-13T11:18:27Z", "losses": 1350, "max_score": 44.51492353136073, "measured_at": null, "min_score": 35.26480634810233, "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": 2864, "rating_method": "sequential_elo", "raw_elo": 1400.1487531575174, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 5, "repaired_rate": 0.20833333333333337, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 36.46271462621648, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 9, "wins": 781 }, { "admitted_plugins": 28, "attempted_matches": 4353, "capped_draws": 225, "codegen_cost_usd": { "admitted_cell_count": 28, "cell_count": 8, "cost_basis_counts": { "local_list_price_estimate": 1, "provider_reported": 48 }, "evidence_basis": "Mixed: Provider-reported + Standard list-price estimate", "failed_cell_count": 4, "max": 0.0370864994, "mean": 0.02452730386875, "median": 0.023468922225, "min": 0.0140238704, "recorded_attempt_count": 48, "run_count": 32, "token_priced_attempt_count": 1, "total": 0.7848737238 }, "codegen_evaluated_cells": 32, "conditional_success_score": 37.57846636346578, "contributing_entrants": null, "distinct_rated_opponents": 2191, "draws": 1173, "entry_count": 28, "failed_game_aliases": [ "GB2-02", "GB2-03", "GB2-07", "GB2-08" ], "first_pass_admitted": 16, "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": "2026-07-13T18:48:15Z", "losses": 1494, "max_score": 49.07869792911936, "measured_at": null, "min_score": 23.621129291107756, "model_code_failure_rate": 0.125, "model_code_failures": 4, "model_display_name": "GLM-5.2", "model_slug": "z-ai-glm-5-2", "plugin_success_rate": 0.875, "provider": "Zhipu", "provider_key": "z-ai", "rank": 40, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 4308, "rating_method": "sequential_elo", "raw_elo": 1522.188442929374, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 12, "repaired_rate": 0.375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 36.34469805232771, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 22, "wins": 1641 }, { "admitted_plugins": 7, "attempted_matches": 1240, "capped_draws": 172, "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": 37.34802155864339, "contributing_entrants": null, "distinct_rated_opponents": 620, "draws": 427, "entry_count": 7, "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": "2026-07-13T11:17:21Z", "losses": 383, "max_score": 79.21328749427038, "measured_at": null, "min_score": 14.026596031966744, "model_code_failure_rate": 0.125, "model_code_failures": 1, "model_display_name": "Qwen3.7 Max", "model_slug": "qwen-qwen3-7-max", "plugin_success_rate": 0.875, "provider": "Alibaba", "provider_key": "qwen", "rank": 41, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1239, "rating_method": "sequential_elo", "raw_elo": 1519.8417904150533, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 36.121819162913, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 429 }, { "admitted_plugins": 7, "attempted_matches": 1002, "capped_draws": 166, "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": 34.81236948125838, "contributing_entrants": null, "distinct_rated_opponents": 508, "draws": 233, "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": "2026-07-13T11:17:55Z", "losses": 358, "max_score": 68.2973627113312, "measured_at": null, "min_score": 10.794214509222783, "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": 986, "rating_method": "sequential_elo", "raw_elo": 1485.246091313927, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 33.6694170817064, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 9, "wins": 395 }, { "admitted_plugins": 25, "attempted_matches": 3793, "capped_draws": 340, "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": 0.0362005625, "mean": 0.024352715625, "median": 0.025206018750000003, "min": 0.016582062499999998, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 49 }, "run_count": 32, "token_priced_attempt_count": 49, "total": 0.7792869 }, "codegen_evaluated_cells": 32, "conditional_success_score": 35.72995441277762, "contributing_entrants": null, "distinct_rated_opponents": 1913, "draws": 1000, "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": "2026-07-13T15:06:27Z", "losses": 1692, "max_score": 52.691719485250296, "measured_at": null, "min_score": 15.263222308732672, "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": 43, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 3776, "rating_method": "sequential_elo", "raw_elo": 1421.0190909788755, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 12, "repaired_rate": 0.375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 33.59154427013184, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 17, "wins": 1084 }, { "admitted_plugins": 6, "attempted_matches": 929, "capped_draws": 47, "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": 34.37636459588008, "contributing_entrants": null, "distinct_rated_opponents": 468, "draws": 189, "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": "2026-07-13T10:52:32Z", "losses": 423, "max_score": 55.02211698080321, "measured_at": null, "min_score": 0.0, "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": 916, "rating_method": "sequential_elo", "raw_elo": 1429.434249707713, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.2857142857142857, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 33.076781883437384, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 3, "wins": 304 }, { "admitted_plugins": 8, "attempted_matches": 1248, "capped_draws": 186, "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-2026-07-12": 10 }, "run_count": 9, "token_priced_attempt_count": 10, "total": 0.6063375 }, "codegen_evaluated_cells": 9, "conditional_success_score": 34.05639297351176, "contributing_entrants": null, "distinct_rated_opponents": 623, "draws": 479, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T16:11:38Z", "losses": 420, "max_score": 54.92953555759788, "measured_at": null, "min_score": 14.71302727158694, "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": 45, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1241, "rating_method": "sequential_elo", "raw_elo": 1471.9612833739554, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 1, "repaired_rate": 0.1111111111111111, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 33.06819712534213, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 3, "wins": 342 }, { "admitted_plugins": 23, "attempted_matches": 2941, "capped_draws": 392, "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": 0.29749325, "mean": 0.24155631250000004, "median": 0.24021375, "min": 0.17873725, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 26 }, "run_count": 24, "token_priced_attempt_count": 26, "total": 5.7973514999999995 }, "codegen_evaluated_cells": 24, "conditional_success_score": 33.04225957146811, "contributing_entrants": null, "distinct_rated_opponents": 1494, "draws": 1194, "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": "2026-07-13T18:48:15Z", "losses": 874, "max_score": 45.74532923505766, "measured_at": null, "min_score": 14.464677503373531, "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": 46, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 2898, "rating_method": "sequential_elo", "raw_elo": 1485.323294563214, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.041666666666666664, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 32.69255681562888, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 34, "wins": 830 }, { "admitted_plugins": 7, "attempted_matches": 1089, "capped_draws": 257, "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-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 1.13802 }, "codegen_evaluated_cells": 8, "conditional_success_score": 32.87543335559842, "contributing_entrants": null, "distinct_rated_opponents": 548, "draws": 539, "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": "2026-07-13T14:18:39Z", "losses": 281, "max_score": 54.81592371456018, "measured_at": null, "min_score": 9.168698365108394, "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": 47, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1080, "rating_method": "sequential_elo", "raw_elo": 1493.3565913362866, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 31.796074035908287, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 8, "wins": 260 }, { "admitted_plugins": 8, "attempted_matches": 1275, "capped_draws": 164, "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": 0.4852846 }, "codegen_evaluated_cells": 8, "conditional_success_score": 31.658220453712367, "contributing_entrants": null, "distinct_rated_opponents": 641, "draws": 452, "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": "2026-07-13T18:28:37Z", "losses": 493, "max_score": 61.07709054345052, "measured_at": null, "min_score": 11.56683145120459, "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": 48, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1263, "rating_method": "sequential_elo", "raw_elo": 1426.6853726769298, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 8, "repaired_rate": 1.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 31.658220453712367, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 3, "wins": 318 }, { "admitted_plugins": 7, "attempted_matches": 1097, "capped_draws": 154, "codegen_cost_usd": { "admitted_cell_count": 7, "cell_count": 8, "cost_basis_counts": { "provider_reported": 14 }, "evidence_basis": "Provider-reported", "failed_cell_count": 2, "max": 0.13485595, "mean": 0.03179205625, "median": 0.0158481, "min": 0.0111232, "recorded_attempt_count": 14, "run_count": 9, "total": 0.3891924 }, "codegen_evaluated_cells": 9, "conditional_success_score": 33.48108617544016, "contributing_entrants": null, "distinct_rated_opponents": 547, "draws": 283, "entry_count": 7, "failed_game_aliases": [ "GB2-02", "GB2-07" ], "first_pass_admitted": 5, "first_pass_rate": 0.5555555555555556, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T18:14:57Z", "losses": 490, "max_score": 64.09572011977573, "measured_at": null, "min_score": 12.512381512184156, "model_code_failure_rate": 0.2222222222222222, "model_code_failures": 2, "model_display_name": "Nemotron 3 Ultra 550B A55B", "model_slug": "nvidia-nemotron-3-ultra-550b-a55b", "plugin_success_rate": 0.7777777777777778, "provider": "NVIDIA", "provider_key": "nvidia", "rank": 49, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1085, "rating_method": "sequential_elo", "raw_elo": 1400.3841885227162, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.2222222222222222, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 31.442235871587773, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 9, "wins": 312 }, { "admitted_plugins": 8, "attempted_matches": 1249, "capped_draws": 141, "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-2026-07-12": 9 }, "run_count": 9, "token_priced_attempt_count": 9, "total": 0.31504800000000005 }, "codegen_evaluated_cells": 9, "conditional_success_score": 31.113379340231347, "contributing_entrants": null, "distinct_rated_opponents": 623, "draws": 428, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T18:48:15Z", "losses": 335, "max_score": 70.48739385233826, "measured_at": null, "min_score": 6.647988945759312, "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": 50, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1242, "rating_method": "sequential_elo", "raw_elo": 1553.2697047814945, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 30.210579319381903, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 4, "wins": 479 }, { "admitted_plugins": 7, "attempted_matches": 1244, "capped_draws": 79, "codegen_cost_usd": { "admitted_cell_count": 7, "cell_count": 8, "cost_basis_counts": { "provider_reported": 14 }, "evidence_basis": "Provider-reported", "failed_cell_count": 2, "max": 0.007539278, "mean": 0.0032457859375, "median": 0.001956843, "min": 0.001266762, "recorded_attempt_count": 14, "run_count": 9, "total": 0.03158643900000001 }, "codegen_evaluated_cells": 9, "conditional_success_score": 30.442194068979944, "contributing_entrants": null, "distinct_rated_opponents": 623, "draws": 359, "entry_count": 7, "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": "2026-07-13T11:15:51Z", "losses": 465, "max_score": 65.10038689956093, "measured_at": null, "min_score": 8.215126650850651, "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": 51, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1243, "rating_method": "sequential_elo", "raw_elo": 1493.0824790183017, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 2, "repaired_rate": 0.2222222222222222, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 28.58839887541176, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 419 }, { "admitted_plugins": 6, "attempted_matches": 973, "capped_draws": 146, "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": 30.719102136050925, "contributing_entrants": null, "distinct_rated_opponents": 451, "draws": 389, "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": "2026-07-13T18:48:15Z", "losses": 258, "max_score": 78.86564479729775, "measured_at": null, "min_score": 3.928336942357347, "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": 52, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 889, "rating_method": "sequential_elo", "raw_elo": 1481.1182426096595, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 28.587345715062675, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 3, "wins": 242 }, { "admitted_plugins": 4, "attempted_matches": 714, "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": 32.6009150084153, "contributing_entrants": null, "distinct_rated_opponents": 357, "draws": 135, "entry_count": 4, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:13:11Z", "losses": 352, "max_score": 54.462035234390775, "measured_at": null, "min_score": 19.649994804578235, "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": 53, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 714, "rating_method": "sequential_elo", "raw_elo": 1376.3819328292898, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 4, "repaired_rate": 0.5714285714285714, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 28.34459639732571, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 227 }, { "admitted_plugins": 11, "attempted_matches": 1966, "capped_draws": 202, "codegen_cost_usd": { "admitted_cell_count": 11, "cell_count": 8, "cost_basis_counts": { "provider_reported": 28 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.017371817999999997, "mean": 0.010146428355, "median": 0.010218342, "min": 0.003562685, "recorded_attempt_count": 28, "run_count": 15, "total": 0.14822491768 }, "codegen_evaluated_cells": 15, "conditional_success_score": 30.22734971003966, "contributing_entrants": null, "distinct_rated_opponents": 984, "draws": 494, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:17:20Z", "losses": 888, "max_score": 63.090428051106514, "measured_at": null, "min_score": 9.719984864483806, "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": 54, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1966, "rating_method": "sequential_elo", "raw_elo": 1410.7235661094926, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 6, "repaired_rate": 0.4, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 27.972122858189454, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 584 }, { "admitted_plugins": 5, "attempted_matches": 872, "capped_draws": 131, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 19 }, "evidence_basis": "Provider-reported", "failed_cell_count": 3, "max": 0.01660212, "mean": 0.008820586750000001, "median": 0.0070236809999999995, "min": 0.00271606, "recorded_attempt_count": 19, "run_count": 8, "total": 0.070564694 }, "codegen_evaluated_cells": 8, "conditional_success_score": 31.118210871946445, "contributing_entrants": null, "distinct_rated_opponents": 437, "draws": 396, "entry_count": 5, "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": "2026-07-13T11:17:15Z", "losses": 247, "max_score": 76.86186232211922, "measured_at": null, "min_score": 7.858209030686404, "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": 55, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 871, "rating_method": "sequential_elo", "raw_elo": 1498.009740982813, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 27.668436835415857, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 228 }, { "admitted_plugins": 6, "attempted_matches": 940, "capped_draws": 133, "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": 29.554104055142627, "contributing_entrants": null, "distinct_rated_opponents": 468, "draws": 261, "entry_count": 6, "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": "2026-07-13T18:48:15Z", "losses": 435, "max_score": 46.68447767783332, "measured_at": null, "min_score": 13.87184383892639, "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": 56, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 921, "rating_method": "sequential_elo", "raw_elo": 1387.397968636173, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 27.503192840124793, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 4, "wins": 225 }, { "admitted_plugins": 5, "attempted_matches": 887, "capped_draws": 171, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 21 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.065385, "mean": 0.03551179375, "median": 0.032728425, "min": 0.0200767, "recorded_attempt_count": 21, "run_count": 9, "total": 0.3177278 }, "codegen_evaluated_cells": 9, "conditional_success_score": 31.17253490312569, "contributing_entrants": null, "distinct_rated_opponents": 445, "draws": 329, "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": "2026-07-13T11:15:55Z", "losses": 343, "max_score": 65.22833892015394, "measured_at": null, "min_score": 10.23547336764388, "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": 57, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 887, "rating_method": "sequential_elo", "raw_elo": 1425.5035909594158, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 5, "repaired_rate": 0.5555555555555556, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 26.91249694943565, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 215 }, { "admitted_plugins": 5, "attempted_matches": 912, "capped_draws": 149, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 20 }, "evidence_basis": "Provider-reported", "failed_cell_count": 3, "max": 0.1121957, "mean": 0.0607572625, "median": 0.060057275, "min": 0.02174195, "recorded_attempt_count": 20, "run_count": 8, "total": 0.4860581000000001 }, "codegen_evaluated_cells": 8, "conditional_success_score": 29.12946837211943, "contributing_entrants": null, "distinct_rated_opponents": 456, "draws": 153, "entry_count": 5, "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": "2026-07-13T11:07:38Z", "losses": 524, "max_score": 50.02655493811615, "measured_at": null, "min_score": 7.242946177185584, "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": 58, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 912, "rating_method": "sequential_elo", "raw_elo": 1324.2847423940475, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 25.90016691576, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 235 }, { "admitted_plugins": 24, "attempted_matches": 3286, "capped_draws": 442, "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-2026-07-12": 29 }, "run_count": 24, "token_priced_attempt_count": 29, "total": 0.4149345000000001 }, "codegen_evaluated_cells": 24, "conditional_success_score": 25.597809333588906, "contributing_entrants": null, "distinct_rated_opponents": 1667, "draws": 1249, "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": "2026-07-13T17:59:25Z", "losses": 1496, "max_score": 45.38475762538517, "measured_at": null, "min_score": 9.599170646265678, "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": 59, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 3256, "rating_method": "sequential_elo", "raw_elo": 1368.073570250796, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 5, "repaired_rate": 0.20833333333333337, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 25.597809333588906, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 30, "wins": 511 }, { "admitted_plugins": 15, "attempted_matches": 2627, "capped_draws": 229, "codegen_cost_usd": { "admitted_cell_count": 15, "cell_count": 8, "cost_basis_counts": { "provider_reported": 48 }, "evidence_basis": "Provider-reported", "failed_cell_count": 6, "max": 0.03389426, "mean": 0.0208777869875, "median": 0.0210709803, "min": 0.0085050301, "recorded_attempt_count": 48, "run_count": 21, "total": 0.43794584700000005 }, "codegen_evaluated_cells": 21, "conditional_success_score": 26.681060316732005, "contributing_entrants": null, "distinct_rated_opponents": 1317, "draws": 1016, "entry_count": 15, "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" ], "infra_failures_excluded": 1, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:14:05Z", "losses": 1100, "max_score": 41.76631544139825, "measured_at": null, "min_score": 13.67840064525899, "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": 60, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 2627, "rating_method": "sequential_elo", "raw_elo": 1385.4478132212687, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 14, "repaired_rate": 0.6666666666666666, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 24.52850481545789, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 511 }, { "admitted_plugins": 25, "attempted_matches": 3638, "capped_draws": 503, "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-2026-07-12": 56 }, "run_count": 32, "token_priced_attempt_count": 56, "total": 0.28794675 }, "codegen_evaluated_cells": 32, "conditional_success_score": 24.45520203265773, "contributing_entrants": null, "distinct_rated_opponents": 1828, "draws": 1315, "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": "2026-07-13T19:18:02Z", "losses": 1449, "max_score": 34.958989185678846, "measured_at": null, "min_score": 8.830356337516129, "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": 61, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 3600, "rating_method": "sequential_elo", "raw_elo": 1416.5645618411584, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 15, "repaired_rate": 0.46875, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 22.99157710151633, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 16, "wins": 836 }, { "admitted_plugins": 5, "attempted_matches": 864, "capped_draws": 208, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 19 }, "evidence_basis": "Provider-reported", "failed_cell_count": 3, "max": 0.0597184625, "mean": 0.02467013555, "median": 0.0239011175, "min": 0.0040410944, "recorded_attempt_count": 19, "run_count": 8, "total": 0.1973610844 }, "codegen_evaluated_cells": 8, "conditional_success_score": 24.89745288066118, "contributing_entrants": null, "distinct_rated_opponents": 433, "draws": 487, "entry_count": 5, "failed_game_aliases": [ "GB2-03", "GB2-05", "GB2-07" ], "first_pass_admitted": 0, "first_pass_rate": 0.0, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:15:45Z", "losses": 255, "max_score": 52.75572069190129, "measured_at": null, "min_score": 11.587783971795917, "model_code_failure_rate": 0.375, "model_code_failures": 3, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": 0.625, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 62, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 864, "rating_method": "sequential_elo", "raw_elo": 1423.5079074524867, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 22.13731391004702, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 122 }, { "admitted_plugins": 5, "attempted_matches": 890, "capped_draws": 127, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 19 }, "evidence_basis": "Provider-reported", "failed_cell_count": 3, "max": 0.0422995, "mean": 0.027492531250000004, "median": 0.025548, "min": 0.0204145, "recorded_attempt_count": 19, "run_count": 8, "total": 0.21994025 }, "codegen_evaluated_cells": 8, "conditional_success_score": 24.39763717968764, "contributing_entrants": null, "distinct_rated_opponents": 445, "draws": 266, "entry_count": 5, "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": "2026-07-13T11:17:51Z", "losses": 450, "max_score": 51.60719199001697, "measured_at": null, "min_score": 6.352808222192618, "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": 63, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 886, "rating_method": "sequential_elo", "raw_elo": 1322.5356017085342, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 21.69290792511931, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 4, "wins": 170 }, { "admitted_plugins": 19, "attempted_matches": 2916, "capped_draws": 275, "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": 22.91569280210852, "contributing_entrants": null, "distinct_rated_opponents": 1479, "draws": 953, "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": "2026-07-13T19:18:02Z", "losses": 1407, "max_score": 34.15933294953593, "measured_at": null, "min_score": 12.636240270675255, "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": 64, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 2894, "rating_method": "sequential_elo", "raw_elo": 1353.1839186520494, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 5, "repaired_rate": 0.20833333333333337, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 21.61566402629856, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 13, "wins": 534 }, { "admitted_plugins": 5, "attempted_matches": 612, "capped_draws": 6, "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": 0.81977125 }, "codegen_evaluated_cells": 8, "conditional_success_score": 23.95203502083948, "contributing_entrants": null, "distinct_rated_opponents": 329, "draws": 22, "entry_count": 5, "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": "2026-07-13T19:18:02Z", "losses": 445, "max_score": 41.07604676062133, "measured_at": null, "min_score": 1.9931136856735752, "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": 65, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 604, "rating_method": "sequential_elo", "raw_elo": 1278.3737896571656, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 21.296705353045024, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 4, "wins": 137 }, { "admitted_plugins": 14, "attempted_matches": 2016, "capped_draws": 291, "codegen_cost_usd": { "admitted_cell_count": 14, "cell_count": 8, "cost_basis_counts": { "provider_reported": 24 }, "evidence_basis": "Provider-reported", "failed_cell_count": 2, "max": 0.004911942999999999, "mean": 0.00318583316625, "median": 0.002947833025, "min": 0.001831717, "recorded_attempt_count": 24, "run_count": 16, "total": 0.05097333066 }, "codegen_evaluated_cells": 16, "conditional_success_score": 21.703418450856987, "contributing_entrants": null, "distinct_rated_opponents": 1023, "draws": 709, "entry_count": 14, "failed_game_aliases": [ "GB2-03", "GB2-04" ], "first_pass_admitted": 10, "first_pass_rate": 0.625, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:18:50Z", "losses": 1008, "max_score": 40.58862492867081, "measured_at": null, "min_score": 6.7491967108184525, "model_code_failure_rate": 0.125, "model_code_failures": 2, "model_display_name": "DeepSeek V4 Flash", "model_slug": "deepseek-deepseek-v4-flash", "plugin_success_rate": 0.875, "provider": "DeepSeek", "provider_key": "deepseek", "rank": 66, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 2001, "rating_method": "sequential_elo", "raw_elo": 1342.6006772277658, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 4, "repaired_rate": 0.25, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 20.990856376900997, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 9, "wins": 284 }, { "admitted_plugins": 6, "attempted_matches": 1076, "capped_draws": 155, "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": 21.582884603762555, "contributing_entrants": null, "distinct_rated_opponents": 538, "draws": 281, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:18:03Z", "losses": 604, "max_score": 38.16566067067517, "measured_at": null, "min_score": 13.28495376492924, "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": 67, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1076, "rating_method": "sequential_elo", "raw_elo": 1274.1875697355829, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 1, "repaired_rate": 0.14285714285714285, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 20.766953540503557, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 191 }, { "admitted_plugins": 7, "attempted_matches": 1238, "capped_draws": 142, "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": 20.378413987999977, "contributing_entrants": null, "distinct_rated_opponents": 620, "draws": 402, "entry_count": 7, "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": "2026-07-13T11:16:26Z", "losses": 619, "max_score": 55.56333293433932, "measured_at": null, "min_score": 5.4413534752207235, "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": 68, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1238, "rating_method": "sequential_elo", "raw_elo": 1320.4337867379556, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 7, "repaired_rate": 0.875, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 19.70935418214024, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 217 }, { "admitted_plugins": 6, "attempted_matches": 1080, "capped_draws": 160, "codegen_cost_usd": { "admitted_cell_count": 6, "cell_count": 8, "cost_basis_counts": { "provider_reported": 18 }, "evidence_basis": "Provider-reported", "failed_cell_count": 2, "max": 0.0149315, "mean": 0.0101355, "median": 0.010566625, "min": 0.00402875, "recorded_attempt_count": 18, "run_count": 8, "total": 0.081084 }, "codegen_evaluated_cells": 8, "conditional_success_score": 20.76901219190074, "contributing_entrants": null, "distinct_rated_opponents": 541, "draws": 282, "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": "2026-07-13T11:17:36Z", "losses": 611, "max_score": 35.400601409407294, "measured_at": null, "min_score": 9.023826409826338, "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": 69, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1079, "rating_method": "sequential_elo", "raw_elo": 1264.5650113951283, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 4, "repaired_rate": 0.5, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 19.327743664533575, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 186 }, { "admitted_plugins": 7, "attempted_matches": 1075, "capped_draws": 164, "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": 19.90626075152395, "contributing_entrants": null, "distinct_rated_opponents": 532, "draws": 449, "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": "2026-07-13T18:14:57Z", "losses": 433, "max_score": 34.62666056621864, "measured_at": null, "min_score": 0.034968617309127016, "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": 70, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1061, "rating_method": "sequential_elo", "raw_elo": 1382.4442262843193, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 19.25270258150882, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 9, "wins": 179 }, { "admitted_plugins": 9, "attempted_matches": 1629, "capped_draws": 298, "codegen_cost_usd": { "admitted_cell_count": 9, "cell_count": 8, "cost_basis_counts": { "provider_reported": 35 }, "evidence_basis": "Provider-reported", "failed_cell_count": 7, "max": 0.045691600000000006, "mean": 0.031545040625, "median": 0.035551075, "min": 0.01864685, "recorded_attempt_count": 35, "run_count": 16, "total": 0.5047206500000001 }, "codegen_evaluated_cells": 16, "conditional_success_score": 21.796342773056757, "contributing_entrants": null, "distinct_rated_opponents": 816, "draws": 729, "entry_count": 9, "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": "2026-07-13T11:23:24Z", "losses": 600, "max_score": 39.49201794250497, "measured_at": null, "min_score": 8.373533192314857, "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": 71, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1614, "rating_method": "sequential_elo", "raw_elo": 1400.9281035855645, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 7, "repaired_rate": 0.4375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 18.87618655106051, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 285 }, { "admitted_plugins": 6, "attempted_matches": 1053, "capped_draws": 33, "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": 20.39523540138827, "contributing_entrants": null, "distinct_rated_opponents": 527, "draws": 312, "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": "2026-07-13T11:18:54Z", "losses": 576, "max_score": 39.79517533017037, "measured_at": null, "min_score": 9.082592792115568, "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": 72, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1052, "rating_method": "sequential_elo", "raw_elo": 1284.49012654842, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.2222222222222222, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 18.42917557278888, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 164 }, { "admitted_plugins": 8, "attempted_matches": 1256, "capped_draws": 164, "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-2026-07-12": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 0.175742 }, "codegen_evaluated_cells": 8, "conditional_success_score": 11.614618741665524, "contributing_entrants": null, "distinct_rated_opponents": 626, "draws": 435, "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": "2026-07-13T18:14:57Z", "losses": 732, "max_score": 21.507682567414136, "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": 73, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1244, "rating_method": "sequential_elo", "raw_elo": 1220.8336508088682, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 11.614618741665524, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 5, "wins": 77 }, { "admitted_plugins": 5, "attempted_matches": 890, "capped_draws": 40, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 13 }, "evidence_basis": "Provider-reported", "failed_cell_count": 3, "max": 0.00870475, "mean": 0.005883593750000001, "median": 0.006313125, "min": 0.003432, "recorded_attempt_count": 13, "run_count": 8, "total": 0.04706874999999999 }, "codegen_evaluated_cells": 8, "conditional_success_score": 11.324732813184706, "contributing_entrants": null, "distinct_rated_opponents": 445, "draws": 191, "entry_count": 5, "failed_game_aliases": [ "GB2-03", "GB2-04", "GB2-08" ], "first_pass_admitted": 3, "first_pass_rate": 0.375, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:18:28Z", "losses": 614, "max_score": 26.3458064931194, "measured_at": null, "min_score": 0.0, "model_code_failure_rate": 0.375, "model_code_failures": 3, "model_display_name": "Gemini 3.1 Flash Lite", "model_slug": "google-gemini-3-1-flash-lite", "plugin_success_rate": 0.625, "provider": "Google", "provider_key": "google", "rank": 74, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 890, "rating_method": "sequential_elo", "raw_elo": 1129.858452273603, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 10.069269592939264, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 85 }, { "admitted_plugins": 4, "attempted_matches": 739, "capped_draws": 8, "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-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 0.375032 }, "codegen_evaluated_cells": 8, "conditional_success_score": 67.76558792775211, "contributing_entrants": null, "distinct_rated_opponents": 370, "draws": 19, "entry_count": 4, "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": 8, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:06:38Z", "losses": 256, "max_score": 75.22709210395418, "measured_at": null, "min_score": 39.765222291989005, "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": 739, "rating_method": "sequential_elo", "raw_elo": 1630.099363957344, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 56.98383996600714, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 464 }, { "admitted_plugins": 7, "attempted_matches": 1126, "capped_draws": 149, "codegen_cost_usd": { "admitted_cell_count": 7, "cell_count": 8, "cost_basis_counts": { "provider_reported": 36 }, "evidence_basis": "Provider-reported", "failed_cell_count": 9, "max": 0.215758025, "mean": 0.16162675, "median": 0.1594081875, "min": 0.098579625, "recorded_attempt_count": 36, "run_count": 16, "total": 2.586028 }, "codegen_evaluated_cells": 16, "conditional_success_score": 38.8658202661972, "contributing_entrants": null, "distinct_rated_opponents": 563, "draws": 430, "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": "2026-07-13T15:25:01Z", "losses": 395, "max_score": 76.96313275824961, "measured_at": null, "min_score": 10.797286233281277, "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": 1094, "rating_method": "sequential_elo", "raw_elo": 1460.6381495389985, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 7, "repaired_rate": 0.4375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 31.609116148077582, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 4, "wins": 269 }, { "admitted_plugins": 4, "attempted_matches": 696, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 4, "cell_count": 8, "cost_basis_counts": { "provider_reported": 19 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.0711619, "mean": 0.0393452125, "median": 0.033877925, "min": 0.02387735, "recorded_attempt_count": 19, "run_count": 8, "total": 0.3147617 }, "codegen_evaluated_cells": 8, "conditional_success_score": 26.55370140303076, "contributing_entrants": null, "distinct_rated_opponents": 348, "draws": 283, "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": "2026-07-13T10:57:42Z", "losses": 258, "max_score": 43.17328153297657, "measured_at": null, "min_score": 9.873513428324548, "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": 696, "rating_method": "sequential_elo", "raw_elo": 1421.3860732227265, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 4, "repaired_rate": 0.5, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 22.328912321526097, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 155 }, { "admitted_plugins": 5, "attempted_matches": 922, "capped_draws": 229, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 30 }, "evidence_basis": "Provider-reported", "failed_cell_count": 11, "max": 0.0, "mean": 0.0, "median": 0.0, "min": 0.0, "recorded_attempt_count": 30, "run_count": 16, "total": 0.0 }, "codegen_evaluated_cells": 16, "conditional_success_score": 24.008686649798452, "contributing_entrants": null, "distinct_rated_opponents": 461, "draws": 229, "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": "2026-07-13T14:59:14Z", "losses": 546, "max_score": 25.03744784818577, "measured_at": null, "min_score": 22.97992545141114, "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": 910, "rating_method": "sequential_elo", "raw_elo": 1242.811947716654, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.125, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 17.950680160249153, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 135 }, { "admitted_plugins": 4, "attempted_matches": 836, "capped_draws": 126, "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": 18.468588629677875, "contributing_entrants": null, "distinct_rated_opponents": 361, "draws": 139, "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": "2026-07-13T11:16:04Z", "losses": 439, "max_score": 25.41066276207961, "measured_at": null, "min_score": 11.1824442971418, "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": 714, "rating_method": "sequential_elo", "raw_elo": 1222.3930169896769, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 15.530169973491637, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 122, "wins": 136 }, { "admitted_plugins": 4, "attempted_matches": 727, "capped_draws": 32, "codegen_cost_usd": { "admitted_cell_count": 4, "cell_count": 8, "cost_basis_counts": { "provider_reported": 14 }, "evidence_basis": "Provider-reported", "failed_cell_count": 5, "max": 0.3927285, "mean": 0.1902770625, "median": 0.16804049999999998, "min": 0.08751, "recorded_attempt_count": 14, "run_count": 9, "total": 1.914945 }, "codegen_evaluated_cells": 9, "conditional_success_score": 18.526079722299833, "contributing_entrants": null, "distinct_rated_opponents": 364, "draws": 32, "entry_count": 4, "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": "2026-07-13T11:15:27Z", "losses": 577, "max_score": 23.94607194601389, "measured_at": null, "min_score": 10.992113891672274, "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": 727, "rating_method": "sequential_elo", "raw_elo": 1137.825653118707, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 2, "repaired_rate": 0.2222222222222222, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 15.12648075125229, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": null, "unilateral_faults": 0, "wins": 118 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 0, "max_score": null, "measured_at": "2026-07-13T11:18:36Z", "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": 177, "rating_method": "sequential_elo", "raw_elo": 2182.455891497867, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 177 }, { "admitted_plugins": 1, "attempted_matches": 181, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 5, "max_score": null, "measured_at": "2026-07-13T11:18:41Z", "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": 175, "rating_method": "sequential_elo", "raw_elo": 2109.1361660112448, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 93.92197991363965, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 170 }, { "admitted_plugins": 1, "attempted_matches": 180, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 87, "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": 11, "max_score": null, "measured_at": "2026-07-13T11:18:43Z", "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": 174, "rating_method": "sequential_elo", "raw_elo": 2063.2330904400105, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 90.1184118419254, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 163 }, { "admitted_plugins": 1, "attempted_matches": 180, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 87, "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": "2026-07-13T11:15:57Z", "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": 174, "rating_method": "sequential_elo", "raw_elo": 1956.8743249905033, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 81.32191846392729, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 152 }, { "admitted_plugins": 1, "attempted_matches": 242, "capped_draws": 20, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 87, "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": 14, "max_score": null, "measured_at": "2026-07-13T11:16:52Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 174, "rating_method": "sequential_elo", "raw_elo": 1927.175418441868, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 78.86564479729775, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 140 }, { "admitted_plugins": 1, "attempted_matches": 180, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 87, "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": "2026-07-13T11:17:35Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 174, "rating_method": "sequential_elo", "raw_elo": 1925.7488185883976, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 78.74765662668415, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 158 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 19, "max_score": null, "measured_at": "2026-07-13T11:16:04Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Luna", "model_slug": "gpt-5-6-luna", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1902.5784711158203, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 76.84550196312736, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 157 }, { "admitted_plugins": 1, "attempted_matches": 178, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-01", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T11:17:45Z", "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": 178, "rating_method": "sequential_elo", "raw_elo": 1895.8385074190176, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 76.30199821690978, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 153 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 41, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 12, "max_score": null, "measured_at": "2026-07-13T11:16:10Z", "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": 177, "rating_method": "sequential_elo", "raw_elo": 1835.462696509623, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 71.30162869957759, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 124 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 13, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 27, "max_score": null, "measured_at": "2026-07-13T11:15:47Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1825.7023228372973, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 70.48739385233826, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 136 }, { "admitted_plugins": 1, "attempted_matches": 178, "capped_draws": 25, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 90, "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": 26, "max_score": null, "measured_at": "2026-07-13T11:18:11Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Sonnet 5", "model_slug": "claude-sonnet-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 178, "rating_method": "sequential_elo", "raw_elo": 1823.6256878798372, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 70.32957472930792, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 127 }, { "admitted_plugins": 1, "attempted_matches": 178, "capped_draws": 40, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 40, "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": "2026-07-13T11:15:33Z", "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": 175, "rating_method": "sequential_elo", "raw_elo": 1809.797470834809, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 69.16491509843954, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 126 }, { "admitted_plugins": 1, "attempted_matches": 178, "capped_draws": 21, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 90, "draws": 21, "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": "2026-07-13T11:16:56Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 178, "rating_method": "sequential_elo", "raw_elo": 1782.8143637430246, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 66.95423898711903, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 125 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 38, "max_score": null, "measured_at": "2026-07-13T11:21:10Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Sol", "model_slug": "gpt-5-6-sol", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1776.8303231553305, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 66.44539299086682, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 134 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 21, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 21, "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": 36, "max_score": null, "measured_at": "2026-07-13T11:15:51Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Hy3 Preview", "model_slug": "tencent-hy3-preview", "plugin_success_rate": null, "provider": "Tencent", "provider_key": "tencent", "rank": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1760.5677988463635, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 65.10038689956093, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 119 }, { "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": 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": 32, "max_score": null, "measured_at": "2026-07-13T11:18:03Z", "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": 0, "rating_method": "sequential_elo", "raw_elo": 1755.6192364630972, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 64.68405752296643, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 126 }, { "admitted_plugins": 1, "attempted_matches": 180, "capped_draws": 39, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 87, "draws": 39, "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": "2026-07-13T11:01:25Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Qwen3.7 Max", "model_slug": "qwen-qwen3-7-max", "plugin_success_rate": null, "provider": "Alibaba", "provider_key": "qwen", "rank": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 174, "rating_method": "sequential_elo", "raw_elo": 1711.0366002104788, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 60.989697523320025, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 110 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 32, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 49, "max_score": null, "measured_at": "2026-07-13T11:18:16Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1702.4467227979674, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 60.293433204479186, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 95 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 8, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 51, "max_score": null, "measured_at": "2026-07-13T11:04:37Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1679.8001706810571, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 58.420430590270925, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 117 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 35, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 38, "max_score": null, "measured_at": "2026-07-13T11:02:25Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1665.9230862388683, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 57.2727143594015, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 103 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 26, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 26, "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": 36, "max_score": null, "measured_at": "2026-07-13T11:01:25Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Sonnet 5", "model_slug": "claude-sonnet-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1663.7071745456506, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 57.08944547269302, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 114 }, { "admitted_plugins": 1, "attempted_matches": 180, "capped_draws": 21, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 87, "draws": 21, "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": 56, "max_score": null, "measured_at": "2026-07-13T11:03:52Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 174, "rating_method": "sequential_elo", "raw_elo": 1644.069321033238, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 55.45111097302008, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 97 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 25, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 49, "max_score": null, "measured_at": "2026-07-13T10:57:43Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Nemotron 3 Ultra 550B A55B", "model_slug": "nvidia-nemotron-3-ultra-550b-a55b", "plugin_success_rate": null, "provider": "NVIDIA", "provider_key": "nvidia", "rank": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1636.2835514611418, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 54.82135108626354, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 102 }, { "admitted_plugins": 1, "attempted_matches": 178, "capped_draws": 12, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 90, "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": 57, "max_score": null, "measured_at": "2026-07-13T10:52:12Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 178, "rating_method": "sequential_elo", "raw_elo": 1608.2690654622086, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 52.518319634361845, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 109 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 48, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 48, "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": 46, "max_score": null, "measured_at": "2026-07-13T10:52:12Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1583.2566182888825, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.43571286891538, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 82 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 57, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 42, "max_score": null, "measured_at": "2026-07-13T10:28:56Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1578.4969194660994, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.04205787490594, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 77 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 29, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 71, "max_score": null, "measured_at": "2026-07-13T10:37:56Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1566.477261696739, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 49.04796171811881, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 76 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 122, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "draws": 122, "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": 13, "max_score": null, "measured_at": "2026-07-13T11:06:43Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 177, "rating_method": "sequential_elo", "raw_elo": 1562.0402297802643, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 48.68798789794065, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 24, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 63, "max_score": null, "measured_at": "2026-07-13T10:47:47Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Qwen3.7 Plus", "model_slug": "qwen-qwen3-7-plus", "plugin_success_rate": null, "provider": "Alibaba", "provider_key": "qwen", "rank": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1555.18352725304, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 48.113903675728, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 89 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 42, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 42, "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": 54, "max_score": null, "measured_at": "2026-07-13T10:39:42Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Nemotron 3 Ultra 550B A55B", "model_slug": "nvidia-nemotron-3-ultra-550b-a55b", "plugin_success_rate": null, "provider": "NVIDIA", "provider_key": "nvidia", "rank": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1548.715871243637, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 47.57899061033618, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 3, "attempted_matches": 368, "capped_draws": 37, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 189, "draws": 37, "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": 123, "max_score": null, "measured_at": "2026-07-13T11:14:09Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 365, "rating_method": "sequential_elo", "raw_elo": 1553.474870529528, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 45.74532923505766, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 31.64168301876909, "unilateral_faults": 3, "wins": 205 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 89, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 89, "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": 46, "max_score": null, "measured_at": "2026-07-13T10:55:38Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1526.3940735456672, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 45.73284709028545, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 118, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 118, "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": 27, "max_score": null, "measured_at": "2026-07-13T11:00:58Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1515.7592394481949, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.85328396900294, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 3, "attempted_matches": 528, "capped_draws": 100, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 264, "draws": 100, "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": 210, "max_score": null, "measured_at": "2026-07-13T11:14:58Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 528, "rating_method": "sequential_elo", "raw_elo": 1511.6681093946452, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.51492353136073, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 218 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 34, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 76, "max_score": null, "measured_at": "2026-07-13T10:47:46Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1511.0191886358589, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.46125398063416, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 66 }, { "admitted_plugins": 2, "attempted_matches": 356, "capped_draws": 204, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 178, "draws": 204, "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": "2026-07-13T11:07:31Z", "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": 354, "rating_method": "sequential_elo", "raw_elo": 1506.5009951955217, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.09453827805331, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 65 }, { "admitted_plugins": 1, "attempted_matches": 178, "capped_draws": 34, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 67, "max_score": null, "measured_at": "2026-07-13T10:29:32Z", "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": 37, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 175, "rating_method": "sequential_elo", "raw_elo": 1505.1064957058, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 43.965185356084454, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 74 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 43, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 43, "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": 75, "max_score": null, "measured_at": "2026-07-13T10:42:32Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5-Pro", "model_slug": "xiaomi-mimo-v2-5-pro", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 38, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1489.682001789536, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 42.69654354980565, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 36, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "draws": 36, "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": 76, "max_score": null, "measured_at": "2026-07-13T10:05:42Z", "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": 39, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 177, "rating_method": "sequential_elo", "raw_elo": 1471.8617528733166, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 41.22969923130028, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 65 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 95, "max_score": null, "measured_at": "2026-07-13T10:08:39Z", "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": 40, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1467.815676585255, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 40.888070274963766, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 79 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 28, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 28, "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": 77, "max_score": null, "measured_at": "2026-07-13T14:59:14Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 41, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1467.0402887330404, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 40.82394115426027, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 71 }, { "admitted_plugins": 4, "attempted_matches": 711, "capped_draws": 86, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 356, "draws": 86, "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": 335, "max_score": null, "measured_at": "2026-07-13T11:13:21Z", "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": 708, "rating_method": "sequential_elo", "raw_elo": 1463.6089955402222, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 40.54710400335003, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 287 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 30, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 70, "max_score": null, "measured_at": "2026-07-13T09:59:28Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT 5", "model_slug": "gpt-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 43, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1454.819819377688, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.8132367021536, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 76 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 93, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 93, "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": 59, "max_score": null, "measured_at": "2026-07-13T11:17:43Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 44, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1447.806674913731, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.23320854391563, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 38, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 80, "max_score": null, "measured_at": "2026-07-13T09:49:22Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Terra", "model_slug": "gpt-5-6-terra", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 45, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1439.664792003006, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 38.55982709946261, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 26, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 26, "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": "2026-07-13T09:52:42Z", "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": 46, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1434.898909401158, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 38.16566067067517, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 70 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 52, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 52, "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": 74, "max_score": null, "measured_at": "2026-07-13T10:25:36Z", "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": 47, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1429.6313610449524, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 37.73000354323659, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugins": 2, "attempted_matches": 364, "capped_draws": 123, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 184, "draws": 123, "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": 148, "max_score": null, "measured_at": "2026-07-13T11:16:10Z", "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": 48, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 360, "rating_method": "sequential_elo", "raw_elo": 1422.5622215473772, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 37.17297425067312, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 89 }, { "admitted_plugins": 3, "attempted_matches": 370, "capped_draws": 82, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 190, "draws": 82, "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": 160, "max_score": null, "measured_at": "2026-07-13T11:15:01Z", "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": 49, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 366, "rating_method": "sequential_elo", "raw_elo": 1448.8989869373763, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 37.098602648581995, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 31.64168301876909, "unilateral_faults": 4, "wins": 124 }, { "admitted_plugins": 2, "attempted_matches": 353, "capped_draws": 73, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 177, "draws": 73, "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": 171, "max_score": null, "measured_at": "2026-07-13T10:08:24Z", "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": 50, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 353, "rating_method": "sequential_elo", "raw_elo": 1418.9687991737023, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 36.85164453712511, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 109 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 32, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 85, "max_score": null, "measured_at": "2026-07-13T09:10:02Z", "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": 51, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1415.7038044424205, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 36.578112968838866, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 59 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 81, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 81, "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": 66, "max_score": null, "measured_at": "2026-07-13T10:33:59Z", "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": 52, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1401.4664634495978, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 35.400601409407294, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 4, "attempted_matches": 552, "capped_draws": 100, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 278, "draws": 100, "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": 242, "max_score": null, "measured_at": "2026-07-13T10:41:40Z", "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": 53, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 541, "rating_method": "sequential_elo", "raw_elo": 1414.4520262624924, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.958989185678846, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 21.337361218395134, "unilateral_faults": 5, "wins": 199 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 67, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 67, "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": 90, "max_score": null, "measured_at": "2026-07-13T11:16:56Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 54, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1336.2354430799348, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 30.005613640447077, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugins": 1, "attempted_matches": 184, "capped_draws": 42, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 92, "draws": 42, "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": 105, "max_score": null, "measured_at": "2026-07-13T11:18:01Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Nemotron 3 Ultra 550B A55B", "model_slug": "nvidia-nemotron-3-ultra-550b-a55b", "plugin_success_rate": null, "provider": "NVIDIA", "provider_key": "nvidia", "rank": 55, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 180, "rating_method": "sequential_elo", "raw_elo": 1335.819638015444, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 29.998854107361183, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 2, "attempted_matches": 195, "capped_draws": 43, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 102, "draws": 43, "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": 127, "max_score": null, "measured_at": "2026-07-13T10:52:17Z", "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": 56, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 190, "rating_method": "sequential_elo", "raw_elo": 1346.9560134273563, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 27.71826139168774, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 44.9403104781061, "unilateral_faults": 5, "wins": 20 }, { "admitted_plugins": 2, "attempted_matches": 353, "capped_draws": 96, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 177, "draws": 96, "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": 216, "max_score": null, "measured_at": "2026-07-13T11:13:02Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4 Nano", "model_slug": "gpt-5-4-nano", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 57, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 353, "rating_method": "sequential_elo", "raw_elo": 1286.6750551799237, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.910176402612787, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugins": 1, "attempted_matches": 279, "capped_draws": 8, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "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": 106, "max_score": null, "measured_at": "2026-07-13T10:36:10Z", "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": 58, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 157, "rating_method": "sequential_elo", "raw_elo": 1282.434152108439, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.41066276207961, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 122, "wins": 43 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 37, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 37, "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": 102, "max_score": null, "measured_at": "2026-07-13T10:29:49Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-OSS 120B", "model_slug": "openai-gpt-oss-120b", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 59, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1266.7890787076983, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 24.261992212117935, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 2, "attempted_matches": 352, "capped_draws": 38, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 176, "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": 223, "max_score": null, "measured_at": "2026-07-13T11:05:30Z", "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": 60, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 352, "rating_method": "sequential_elo", "raw_elo": 1259.3008354454205, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.642670598228595, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 91 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 12, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 123, "max_score": null, "measured_at": "2026-07-13T10:03:12Z", "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": 61, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1256.888916122614, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.44319073155597, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugins": 2, "attempted_matches": 360, "capped_draws": 97, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 180, "draws": 97, "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": 209, "max_score": null, "measured_at": "2026-07-13T14:59:14Z", "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": 62, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 356, "rating_method": "sequential_elo", "raw_elo": 1251.1205188144445, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 22.979925451411145, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 45, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 45, "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": 113, "max_score": null, "measured_at": "2026-07-13T10:33:36Z", "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": 63, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1233.5801986986205, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 21.515423164837383, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 75, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "draws": 75, "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": 100, "max_score": null, "measured_at": "2026-07-13T10:53:33Z", "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": 64, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 177, "rating_method": "sequential_elo", "raw_elo": 1222.387305610914, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.59670002292491, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 27, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 124, "max_score": null, "measured_at": "2026-07-13T10:43:12Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT 5", "model_slug": "gpt-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 65, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1202.6591487315732, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.95807107329767, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 33, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 121, "max_score": null, "measured_at": "2026-07-13T10:36:46Z", "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": 66, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1199.5170400431791, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.698200265719244, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 1, "attempted_matches": 178, "capped_draws": 39, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 39, "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": 118, "max_score": null, "measured_at": "2026-07-13T11:07:07Z", "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": 67, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 175, "rating_method": "sequential_elo", "raw_elo": 1165.1188661834126, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.84621538632902, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 4, "attempted_matches": 707, "capped_draws": 121, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 355, "draws": 121, "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": 516, "max_score": null, "measured_at": "2026-07-13T11:18:43Z", "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": 68, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 707, "rating_method": "sequential_elo", "raw_elo": 1157.921326676557, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.26322230873267, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 70 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 40, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 40, "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": 125, "max_score": null, "measured_at": "2026-07-13T10:55:07Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Gemini 3.1 Flash Lite", "model_slug": "google-gemini-3-1-flash-lite", "plugin_success_rate": null, "provider": "Google", "provider_key": "google", "rank": 69, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1143.1552701268488, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.03675150081587, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 32, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 131, "max_score": null, "measured_at": "2026-07-13T11:04:49Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1106.3424308016235, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.992113891672274, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 13, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 147, "max_score": null, "measured_at": "2026-07-13T10:56:42Z", "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": 71, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1061.0110888178588, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 7.242946177185584, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "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": "2026-07-13T10:41:12Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1979.7616482540543, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 147 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 2, "max_score": null, "measured_at": "2026-07-13T09:00:33Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1755.83086583758, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 60.316068241537906, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 103 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 67, "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": "2026-07-13T08:41:52Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1750.9184381937966, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 59.44513946961022, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 94 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 69, "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": "2026-07-13T08:08:47Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1717.875826669142, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 53.58698477233553, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 93 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 107, "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": "2026-07-13T06:34:01Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1601.2168587128067, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 32.90441007321703, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 54 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 111, "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": "2026-07-13T06:52:43Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1601.040803520877, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 32.87319708786287, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 89, "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": "2026-07-13T06:52:00Z", "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": 162, "rating_method": "sequential_elo", "raw_elo": 1594.983084343725, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 31.782257891449625, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 67 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 118, "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": "2026-07-13T06:14:51Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1574.074206871008, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.075303957431895, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 129, "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": "2026-07-13T05:46:51Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1555.1607564607773, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 24.739081750285404, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 135, "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": "2026-07-13T04:24:13Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Gemini 3.5 Flash", "model_slug": "google-gemini-3-5-flash", "plugin_success_rate": null, "provider": "Google", "provider_key": "google", "rank": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1531.732358251298, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.585439689697196, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugins": 2, "attempted_matches": 326, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 163, "draws": 290, "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": 24, "max_score": null, "measured_at": "2026-07-13T04:09:54Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 326, "rating_method": "sequential_elo", "raw_elo": 1503.0322461375367, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.4970934576409, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 2, "attempted_matches": 325, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 163, "draws": 287, "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": 20, "max_score": null, "measured_at": "2026-07-13T04:22:09Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 325, "rating_method": "sequential_elo", "raw_elo": 1501.245834006424, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.171975712097549, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": 6, "max_score": null, "measured_at": "2026-07-13T03:10:22Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1499.4444060091091, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.877885447048715, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 140, "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": "2026-07-13T03:14:08Z", "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": 162, "rating_method": "sequential_elo", "raw_elo": 1499.0901816144049, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.781317813213978, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 147, "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": "2026-07-13T03:20:13Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1498.7049924286634, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.71302727158694, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 155, "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": "2026-07-13T09:51:53Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1498.3417970308822, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.64863602866253, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 15, "max_score": null, "measured_at": "2026-07-13T03:35:09Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1497.4232144200814, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.519546549031492, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 140, "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": "2026-07-13T03:33:22Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4", "model_slug": "gpt-5-4", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1497.5143688345588, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.518901175227816, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 3, "attempted_matches": 487, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 441, "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": 32, "max_score": null, "measured_at": "2026-07-13T10:05:47Z", "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": 487, "rating_method": "sequential_elo", "raw_elo": 1497.2723001644736, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.464677503373531, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 142, "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": "2026-07-13T03:19:46Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1494.7375477294534, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.026596031966744, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 3, "attempted_matches": 488, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 434, "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": 36, "max_score": null, "measured_at": "2026-07-13T10:08:15Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 488, "rating_method": "sequential_elo", "raw_elo": 1492.8057489565615, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.67840064525899, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 150, "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": "2026-07-13T03:14:14Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1492.3988762701977, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.62877706153271, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 147, "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": "2026-07-13T03:14:46Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1492.0233169987628, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.562193816185417, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 151, "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": "2026-07-13T03:20:15Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1490.2321929984787, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.244643810555974, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 142, "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": "2026-07-13T03:09:51Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1489.0269354516097, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.03096260214575, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 3, "attempted_matches": 488, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 440, "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": 36, "max_score": null, "measured_at": "2026-07-13T10:05:40Z", "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": 488, "rating_method": "sequential_elo", "raw_elo": 1489.1504626235194, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.030351601501769, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 155, "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": "2026-07-13T03:20:50Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Qwen3.7 Plus", "model_slug": "qwen-qwen3-7-plus", "plugin_success_rate": null, "provider": "Alibaba", "provider_key": "qwen", "rank": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1488.9036829035151, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.009111045617562, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 147, "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": "2026-07-13T03:20:30Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1487.6089971420777, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 12.76276880459896, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 138, "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": 18, "max_score": null, "measured_at": "2026-07-13T03:10:13Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1486.2616894159742, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 12.540709613495318, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 147, "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": "2026-07-13T02:43:13Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1481.07722300102, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.587783971795917, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 12, "max_score": null, "measured_at": "2026-07-13T02:44:51Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1480.7685811844883, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.56683145120459, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 150, "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": "2026-07-13T02:42:09Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Luna", "model_slug": "gpt-5-6-luna", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1479.88166278555, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.37582201210324, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 151, "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": "2026-07-13T02:39:53Z", "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": 162, "rating_method": "sequential_elo", "raw_elo": 1477.473010095113, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.94878978246065, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 147, "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": "2026-07-13T10:34:56Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1476.895887324943, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.846471160808935, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 124, "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": 31, "max_score": null, "measured_at": "2026-07-13T10:25:55Z", "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": 162, "rating_method": "sequential_elo", "raw_elo": 1476.6184623443564, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.797286233281277, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 7 }, { "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": 46, "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": 3, "max_score": null, "measured_at": "2026-07-08T14:06:26Z", "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": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 69, "rating_method": "sequential_elo", "raw_elo": 1493.0798628212344, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.794214509222783, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 16.01143046671968, "unilateral_faults": 5, "wins": 4 }, { "admitted_plugins": 3, "attempted_matches": 488, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 421, "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": 41, "max_score": null, "measured_at": "2026-07-13T10:41:12Z", "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": 488, "rating_method": "sequential_elo", "raw_elo": 1475.7825576526072, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.660343551755462, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 136, "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": "2026-07-13T03:21:44Z", "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": 162, "rating_method": "sequential_elo", "raw_elo": 1475.1452511629736, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.536099280916575, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 150, "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": "2026-07-13T03:11:47Z", "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": 39, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1474.5585295004312, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.465845731109994, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": 13, "max_score": null, "measured_at": "2026-07-13T02:42:15Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT 4.1", "model_slug": "gpt-4-1", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 40, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1474.2382944956544, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.392264752412776, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 151, "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": "2026-07-13T03:02:27Z", "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": 41, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1473.2591263768556, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.23547336764388, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 147, "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": "2026-07-13T03:15:32Z", "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": 42, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1472.726349126907, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.124210580685428, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 150, "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": "2026-07-13T03:17:22Z", "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": 43, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1471.6661923172385, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.95306063713581, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 145, "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": "2026-07-13T03:20:57Z", "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": 44, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1471.674689049943, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.920800162399148, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 152, "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": "2026-07-13T03:18:32Z", "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": 45, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1471.2175104960083, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.873513428324548, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 326, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 163, "draws": 291, "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": 24, "max_score": null, "measured_at": "2026-07-13T03:46:25Z", "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": 46, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 326, "rating_method": "sequential_elo", "raw_elo": 1470.4467708737575, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.719984864483806, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 3, "attempted_matches": 488, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 443, "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": 41, "max_score": null, "measured_at": "2026-07-13T10:26:32Z", "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": 47, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 488, "rating_method": "sequential_elo", "raw_elo": 1469.7970680422186, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.599170646265678, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 151, "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": "2026-07-13T03:48:37Z", "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": 164, "rating_method": "sequential_elo", "raw_elo": 1467.242038434574, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.168698365108394, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 12, "max_score": null, "measured_at": "2026-07-13T03:35:28Z", "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": 49, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1467.129706579994, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.13197672529834, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 17, "max_score": null, "measured_at": "2026-07-13T03:32:04Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1466.8511591185422, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.082592792115568, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 4, "attempted_matches": 650, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 325, "draws": 585, "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": 57, "max_score": null, "measured_at": "2026-07-13T10:26:17Z", "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": 51, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 650, "rating_method": "sequential_elo", "raw_elo": 1465.476483309628, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 8.83035633751613, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 150, "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": "2026-07-13T03:26:22Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 52, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1465.213111145169, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 8.792181774741303, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 150, "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": "2026-07-13T03:30:54Z", "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": 53, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1464.8321092855726, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 8.707672962746242, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 2, "attempted_matches": 326, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 163, "draws": 297, "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": 25, "max_score": null, "measured_at": "2026-07-13T10:28:30Z", "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": 326, "rating_method": "sequential_elo", "raw_elo": 1462.852181478415, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 8.373533192314857, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 136, "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": 23, "max_score": null, "measured_at": "2026-07-13T03:35:49Z", "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": 55, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1461.958262259751, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 8.215126650850651, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 3, "attempted_matches": 487, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 421, "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": 54, "max_score": null, "measured_at": "2026-07-13T10:32:45Z", "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": 56, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 487, "rating_method": "sequential_elo", "raw_elo": 1461.1149562623204, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 8.054309065535916, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 19, "max_score": null, "measured_at": "2026-07-13T03:45:11Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1459.9450873132312, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 7.858209030686404, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 141, "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": "2026-07-13T03:49:55Z", "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": 58, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1457.8254805779036, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 7.482422021730727, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 325, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 163, "draws": 289, "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": 35, "max_score": null, "measured_at": "2026-07-13T04:19:50Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "DeepSeek V4 Flash", "model_slug": "deepseek-deepseek-v4-flash", "plugin_success_rate": null, "provider": "DeepSeek", "provider_key": "deepseek", "rank": 59, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 325, "rating_method": "sequential_elo", "raw_elo": 1454.35494993586, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 6.858648160115894, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 2, "attempted_matches": 324, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 162, "draws": 282, "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": 37, "max_score": null, "measured_at": "2026-07-13T09:59:46Z", "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": 60, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 324, "rating_method": "sequential_elo", "raw_elo": 1453.7854276397609, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 6.7491967108184525, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 141, "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": 22, "max_score": null, "measured_at": "2026-07-13T04:41:25Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Hy3 Preview", "model_slug": "tencent-hy3-preview", "plugin_success_rate": null, "provider": "Tencent", "provider_key": "tencent", "rank": 61, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1437.778851789159, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 3.928336942357347, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 132, "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": 24, "max_score": null, "measured_at": "2026-07-13T05:22:21Z", "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": 62, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1415.5264805634315, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 0.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 31, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-03", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T08:09:45Z", "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": 24, "rating_method": "sequential_elo", "raw_elo": 1647.444720026088, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 56.25, "unilateral_faults": 1, "wins": 19 }, { "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": 31, "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": "2026-07-13T07:06:20Z", "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": 42, "rating_method": "sequential_elo", "raw_elo": 1591.4081011424776, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 87.5163455191311, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 1, "attempted_matches": 23, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 12, "draws": 4, "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": "2026-07-13T05:22:49Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 14, "rating_method": "sequential_elo", "raw_elo": 1573.2670768093667, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 67.15032789851486, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 85.34944487358055, "unilateral_faults": 3, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 28, "capped_draws": 1, "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": "GB2-03", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T18:28:37Z", "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": 19, "rating_method": "sequential_elo", "raw_elo": 1530.0797129244056, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 57.25721379782891, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 68.05339887498948, "unilateral_faults": 6, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 25, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-03", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-09T08:32:42Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 15, "rating_method": "sequential_elo", "raw_elo": 1534.5522330380682, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 55.20623759020802, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 81.25, "unilateral_faults": 3, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 47, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "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": 12, "max_score": null, "measured_at": "2026-07-13T05:22:45Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1491.5723107308593, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 54.32702967567564, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 29, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 17, "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": 2, "max_score": null, "measured_at": "2026-07-13T17:37:51Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 17, "rating_method": "sequential_elo", "raw_elo": 1520.9383308199456, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 52.545153513088835, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 74.10113019775793, "unilateral_faults": 9, "wins": 4 }, { "admitted_plugins": 2, "attempted_matches": 49, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 32, "draws": 15, "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": "2026-07-13T19:18:02Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 33, "rating_method": "sequential_elo", "raw_elo": 1515.0533936190836, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.021467175110054, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 76.10393346764043, "unilateral_faults": 7, "wins": 11 }, { "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": 19, "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": 7, "max_score": null, "measured_at": "2026-07-13T18:28:37Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 22, "rating_method": "sequential_elo", "raw_elo": 1495.139483110263, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 47.51485346996474, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 60.5072070285374, "unilateral_faults": 3, "wins": 6 }, { "admitted_plugins": 3, "attempted_matches": 48, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 32, "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": 4, "max_score": null, "measured_at": "2026-07-13T17:59:25Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1525.1695248876265, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 45.38475762538517, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 94.9352233375065, "unilateral_faults": 16, "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": 1, "distinct_rated_opponents": 14, "draws": 6, "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": "2026-07-13T18:48:15Z", "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": 14, "rating_method": "sequential_elo", "raw_elo": 1506.600847615336, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.679296623862335, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 85.34944487358055, "unilateral_faults": 3, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 27, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 17, "draws": 5, "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": "2026-07-09T08:02:11Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 17, "rating_method": "sequential_elo", "raw_elo": 1493.3081962704764, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 43.2319281351103, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 74.10113019775793, "unilateral_faults": 3, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 23, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 12, "draws": 6, "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": 3, "max_score": null, "measured_at": "2026-07-13T19:18:02Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 12, "rating_method": "sequential_elo", "raw_elo": 1509.940922087195, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 43.223026423674064, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 94.92504905630727, "unilateral_faults": 4, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 27, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 11, "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": 4, "max_score": null, "measured_at": "2026-07-13T18:48:15Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 11, "rating_method": "sequential_elo", "raw_elo": 1514.2292928833303, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 43.1415761094804, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 3, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 25, "capped_draws": 3, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 8, "draws": 4, "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": 1, "max_score": null, "measured_at": "2026-07-13T19:18:02Z", "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": 8, "rating_method": "sequential_elo", "raw_elo": 1530.8524840939854, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 42.723582427118195, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 5, "wins": 3 }, { "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": 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": 7, "max_score": null, "measured_at": "2026-07-10T16:22:35Z", "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": 25, "rating_method": "sequential_elo", "raw_elo": 1475.1051868078084, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 42.43356332444173, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 54.30806756909202, "unilateral_faults": 3, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 10, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 6, "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": 1, "max_score": null, "measured_at": "2026-07-13T16:11:38Z", "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": 6, "rating_method": "sequential_elo", "raw_elo": 1546.1471946417246, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 41.86144914266503, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 3, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 23, "capped_draws": 3, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 12, "draws": 8, "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": "2026-07-13T17:59:25Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 12, "rating_method": "sequential_elo", "raw_elo": 1504.948568600018, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 41.54026541107848, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 94.92504905630727, "unilateral_faults": 4, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 25, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 18, "draws": 5, "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": "2026-07-13T19:18:02Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Nex N2 Pro", "model_slug": "nex-agi-nex-n2-pro", "plugin_success_rate": null, "provider": "Nex AGI", "provider_key": "nex-agi", "rank": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 18, "rating_method": "sequential_elo", "raw_elo": 1484.3975960830628, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 41.07604676062133, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 70.95786693528086, "unilateral_faults": 3, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 20, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 6, "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": 0, "max_score": null, "measured_at": "2026-07-13T19:18:02Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 6, "rating_method": "sequential_elo", "raw_elo": 1542.3878676490287, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 40.594301511161184, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 11, "wins": 3 }, { "admitted_plugins": 3, "attempted_matches": 57, "capped_draws": 9, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 32, "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": 5, "max_score": null, "measured_at": "2026-07-13T18:48:15Z", "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": 32, "rating_method": "sequential_elo", "raw_elo": 1512.3501346703968, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 40.42772895701176, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 92.50593750605547, "unilateral_faults": 16, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 13, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 8, "draws": 5, "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": 1, "max_score": null, "measured_at": "2026-07-13T19:18:02Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 8, "rating_method": "sequential_elo", "raw_elo": 1519.869789486925, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.021671024915825, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 4, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 17, "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": 7, "max_score": null, "measured_at": "2026-07-13T18:48:15Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 21, "rating_method": "sequential_elo", "raw_elo": 1469.7386447583692, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 38.321211372267925, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 62.850358177805205, "unilateral_faults": 4, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 18, "draws": 16, "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": "2026-07-13T15:25:01Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 21, "rating_method": "sequential_elo", "raw_elo": 1465.3321920823437, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 36.835938587376226, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 62.850358177805205, "unilateral_faults": 4, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 10, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 4, "draws": 0, "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": 0, "max_score": null, "measured_at": "2026-07-13T18:48:15Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 4, "rating_method": "sequential_elo", "raw_elo": 1558.899979460019, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 36.823344296143375, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 3, "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": 1, "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": "GB2-03", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-08T11:20:47Z", "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": 17, "rating_method": "sequential_elo", "raw_elo": 1473.9712875944372, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 36.71408117019925, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 74.10113019775793, "unilateral_faults": 3, "wins": 3 }, { "admitted_plugins": 3, "attempted_matches": 56, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "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": "GB2-03", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T18:48:15Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 34, "rating_method": "sequential_elo", "raw_elo": 1499.7508607904936, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 35.93453545842982, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 89.35113295832984, "unilateral_faults": 17, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 17, "draws": 16, "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": "2026-07-13T15:06:27Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 22, "rating_method": "sequential_elo", "raw_elo": 1456.417964127742, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.46308086219, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 60.5072070285374, "unilateral_faults": 3, "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": 4, "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": 0, "max_score": null, "measured_at": "2026-07-13T17:37:51Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 4, "rating_method": "sequential_elo", "raw_elo": 1548.1853629901475, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 33.21179336996703, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 9, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 25, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 16, "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": 5, "max_score": null, "measured_at": "2026-07-13T14:18:39Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.5", "model_slug": "gpt-5-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 16, "rating_method": "sequential_elo", "raw_elo": 1456.4708771844437, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 29.893935867832372, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 77.5178125181665, "unilateral_faults": 8, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 18, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 6, "draws": 4, "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": 1, "max_score": null, "measured_at": "2026-07-13T18:14:57Z", "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": 6, "rating_method": "sequential_elo", "raw_elo": 1501.8089182415472, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 26.916449137448275, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 9, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 12, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 7, "draws": 4, "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": "2026-07-06T04:25:17Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Qwen3.7 Max", "model_slug": "qwen-qwen3-7-max", "plugin_success_rate": null, "provider": "Alibaba", "provider_key": "qwen", "rank": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 7, "rating_method": "sequential_elo", "raw_elo": 1488.270588881205, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.64439063164653, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 4, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 15, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 4, "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": 0, "max_score": null, "measured_at": "2026-07-06T04:10:11Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 4, "rating_method": "sequential_elo", "raw_elo": 1519.7751984555318, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.63564509379393, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 9, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 14, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 4, "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": 0, "max_score": null, "measured_at": "2026-07-13T18:14:57Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 4, "rating_method": "sequential_elo", "raw_elo": 1516.5700531655325, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 22.55529420366387, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 10, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 14, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 4, "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": 1, "max_score": null, "measured_at": "2026-07-13T15:25:01Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 4, "rating_method": "sequential_elo", "raw_elo": 1515.5611346513658, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 22.215220379787834, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 5, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 16, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 7, "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": 4, "max_score": null, "measured_at": "2026-07-13T18:14:57Z", "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": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 7, "rating_method": "sequential_elo", "raw_elo": 1475.9979555272569, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 21.507682567414136, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 5, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 23, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 12, "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": 7, "max_score": null, "measured_at": "2026-07-13T14:18:39Z", "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": 12, "rating_method": "sequential_elo", "raw_elo": 1443.5649425457402, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.849828926322857, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 94.92504905630727, "unilateral_faults": 5, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 29, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 12, "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": 8, "max_score": null, "measured_at": "2026-07-08T19:50:24Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4", "model_slug": "gpt-5-4", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 38, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 14, "rating_method": "sequential_elo", "raw_elo": 1435.806116874855, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.816680906992, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 85.34944487358055, "unilateral_faults": 3, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 9, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 4, "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": 1, "max_score": null, "measured_at": "2026-07-10T13:21:23Z", "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": 39, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 4, "rating_method": "sequential_elo", "raw_elo": 1505.6825279027676, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.885461311644505, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 3, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 12, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 5, "draws": 4, "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": 1, "max_score": null, "measured_at": "2026-07-13T16:11:38Z", "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": 40, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 5, "rating_method": "sequential_elo", "raw_elo": 1482.759212617988, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.412330591049, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 3, "wins": 0 }, { "admitted_plugins": 3, "attempted_matches": 67, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 34, "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": 26, "max_score": null, "measured_at": "2026-07-13T19:18:02Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4 Nano", "model_slug": "gpt-5-4-nano", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 41, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 45, "rating_method": "sequential_elo", "raw_elo": 1426.644809610924, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.56210066612941, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 76.96791901759822, "unilateral_faults": 6, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 9, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 3, "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": 1, "max_score": null, "measured_at": "2026-07-10T13:33:30Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Sol", "model_slug": "gpt-5-6-sol", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 42, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 3, "rating_method": "sequential_elo", "raw_elo": 1507.1991778484949, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 12.279638610710084, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 4, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 11, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 6, "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": 3, "max_score": null, "measured_at": "2026-07-11T21:30:40Z", "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": 43, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 6, "rating_method": "sequential_elo", "raw_elo": 1458.1502679833463, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 12.20052913984636, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 4, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 9, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 6, "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": 3, "max_score": null, "measured_at": "2026-07-13T15:06:27Z", "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": 6, "rating_method": "sequential_elo", "raw_elo": 1456.317551717083, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.582779718067748, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 3, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 25, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 14, "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": "2026-07-13T02:19:36Z", "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": 20, "rating_method": "sequential_elo", "raw_elo": 1387.519862012822, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.931466072572777, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 65.3589451179962, "unilateral_faults": 1, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 11, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 4, "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": 2, "max_score": null, "measured_at": "2026-07-13T18:48:15Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Luna", "model_slug": "gpt-5-6-luna", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 46, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 4, "rating_method": "sequential_elo", "raw_elo": 1469.3768449312888, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 6.647988945759312, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 4, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 17, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 3, "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": 2, "max_score": null, "measured_at": "2026-07-13T18:14:57Z", "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": 47, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 3, "rating_method": "sequential_elo", "raw_elo": 1470.872141220401, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 0.034968617309127016, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 9, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 8, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 2, "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": 0, "max_score": null, "measured_at": "2026-07-06T04:21:24Z", "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": 48, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 2, "rating_method": "sequential_elo", "raw_elo": 1501.7085052884202, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 0.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 100.0, "unilateral_faults": 6, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 18, "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": "2026-07-13T10:40:55Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1950.1957259270505, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 143 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 75, "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": "2026-07-13T08:02:34Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1682.9421776365198, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 53.980008192328675, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 76, "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": "2026-07-13T08:04:55Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1664.2766188843018, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.7494004136231, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 95, "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": "2026-07-13T07:20:52Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1613.9588680555748, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 42.101358265742746, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 107, "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": "2026-07-13T06:51:02Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1570.6589170900013, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.64527994066829, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 113, "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": "2026-07-13T06:42:32Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1564.3358756481528, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 33.556477501132086, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 92, "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": 16, "max_score": null, "measured_at": "2026-07-13T06:44:30Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Terra", "model_slug": "gpt-5-6-terra", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1559.5330174908072, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 32.71297130401039, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 54 }, { "admitted_plugins": 2, "attempted_matches": 324, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 162, "draws": 201, "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": 46, "max_score": null, "measured_at": "2026-07-13T09:47:56Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 324, "rating_method": "sequential_elo", "raw_elo": 1548.0368493178066, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 30.733377137627382, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 77 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 79, "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": "2026-07-13T05:41:08Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1543.8369658067368, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 30.02664723694179, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 67 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 115, "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": "2026-07-13T06:16:10Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Sol", "model_slug": "gpt-5-6-sol", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1542.572370442649, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 29.792415737202536, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 97, "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": 26, "max_score": null, "measured_at": "2026-07-13T05:55:03Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1540.2910960595405, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 29.39958941518281, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugins": 3, "attempted_matches": 487, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 339, "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": 47, "max_score": null, "measured_at": "2026-07-13T09:15:55Z", "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": 487, "rating_method": "sequential_elo", "raw_elo": 1527.2539298459496, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 27.160132630433424, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 101 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 119, "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": "2026-07-13T05:32:22Z", "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": 162, "rating_method": "sequential_elo", "raw_elo": 1525.5768328644149, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 26.86585216070314, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 130, "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": "2026-07-13T06:10:45Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1525.012217087992, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 26.80142407302904, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 133, "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": "2026-07-13T05:29:14Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1519.6885679503296, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.88471298997989, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 100, "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": "2026-07-13T05:07:18Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1518.7080841668571, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.699554352300087, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 112, "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": "2026-07-13T05:24:05Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Sonnet 5", "model_slug": "claude-sonnet-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1517.3293852666695, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.46214791748297, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 133, "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": "2026-07-13T05:22:03Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1515.3498397518797, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.12127809945343, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "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": 22, "max_score": null, "measured_at": "2026-07-13T05:17:57Z", "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": 162, "rating_method": "sequential_elo", "raw_elo": 1515.2953296100363, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.095418433766493, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 125, "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": "2026-07-13T05:27:28Z", "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": 162, "rating_method": "sequential_elo", "raw_elo": 1514.9568544895735, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.03713437216872, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 33, "max_score": null, "measured_at": "2026-07-13T05:27:45Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "DeepSeek V4 Pro", "model_slug": "deepseek-deepseek-v4-pro", "plugin_success_rate": null, "provider": "DeepSeek", "provider_key": "deepseek", "rank": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1514.6418355739393, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 24.99936261254212, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 135, "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": "2026-07-13T05:34:31Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-OSS 120B", "model_slug": "openai-gpt-oss-120b", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1513.2373943667817, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 24.77384670826449, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 141, "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": "2026-07-13T05:32:34Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1510.7262694584142, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 24.30864455521044, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 121, "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": "2026-07-13T05:05:18Z", "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": 164, "rating_method": "sequential_elo", "raw_elo": 1507.7579377901347, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.83030620756496, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 124, "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": "2026-07-13T05:16:55Z", "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": 164, "rating_method": "sequential_elo", "raw_elo": 1507.0146083284037, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.702307848111612, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 4, "attempted_matches": 649, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 325, "draws": 488, "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": 79, "max_score": null, "measured_at": "2026-07-13T10:04:30Z", "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": 649, "rating_method": "sequential_elo", "raw_elo": 1506.709721011585, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.621129291107756, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 82 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 102, "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": "2026-07-13T04:41:41Z", "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": 164, "rating_method": "sequential_elo", "raw_elo": 1505.1771434461737, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.38590374658337, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 135, "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": "2026-07-13T05:21:40Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1500.6347515214338, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 22.587398777192348, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 126, "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": "2026-07-13T05:11:21Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1495.4302921877209, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 21.69121170153766, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 120, "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": "2026-07-13T04:48:59Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1492.984523164819, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 21.27006006064328, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 3, "attempted_matches": 488, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 338, "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": 87, "max_score": null, "measured_at": "2026-07-13T10:00:01Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 488, "rating_method": "sequential_elo", "raw_elo": 1492.9971527865705, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 21.266693757024104, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 63 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 144, "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": "2026-07-13T04:57:31Z", "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": 164, "rating_method": "sequential_elo", "raw_elo": 1492.0699499263617, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 21.1288974607488, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "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": 27, "max_score": null, "measured_at": "2026-07-13T04:31:47Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1491.2502398452857, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.95495017406873, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 100, "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": 34, "max_score": null, "measured_at": "2026-07-13T04:40:15Z", "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1491.0580523341491, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.954652743693853, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 120, "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": 25, "max_score": null, "measured_at": "2026-07-13T04:41:57Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1488.5008874765424, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.49799593291555, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 125, "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": 16, "max_score": null, "measured_at": "2026-07-13T04:57:33Z", "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": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1488.4671596795529, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.475714903867996, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 138, "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": "2026-07-13T04:51:47Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Sonnet 5", "model_slug": "claude-sonnet-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 37, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1487.9874078589992, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.42590004987722, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 135, "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": "2026-07-13T04:49:51Z", "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": 38, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1487.6486598737995, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.367569002063373, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 124, "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": "2026-07-13T04:51:27Z", "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": 39, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1485.9799093066515, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.08021683061268, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 27, "max_score": null, "measured_at": "2026-07-13T04:50:17Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 40, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1484.21303296907, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.759644541255607, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "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": 11, "max_score": null, "measured_at": "2026-07-13T10:00:51Z", "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": 41, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1483.3666845551031, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.597433493036245, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 110, "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": "2026-07-13T04:39:23Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.5", "model_slug": "gpt-5-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 42, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1483.040140420163, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.541203899412803, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 37, "max_score": null, "measured_at": "2026-07-13T04:47:28Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT 5", "model_slug": "gpt-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 43, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1482.694962951085, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.514562210351176, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 125, "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": "2026-07-13T04:45:16Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Gemma 4 31B", "model_slug": "google-gemma-4-31b-it", "plugin_success_rate": null, "provider": "Google", "provider_key": "google", "rank": 44, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1482.0576367562858, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.404817189373603, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 2, "attempted_matches": 324, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 162, "draws": 139, "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": 90, "max_score": null, "measured_at": "2026-07-13T10:26:14Z", "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": 45, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 324, "rating_method": "sequential_elo", "raw_elo": 1480.1147879033615, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.037469899550587, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 95 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 23, "max_score": null, "measured_at": "2026-07-13T04:44:59Z", "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": 46, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1479.8246362268771, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.02030343183053, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugins": 2, "attempted_matches": 324, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 162, "draws": 241, "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": 48, "max_score": null, "measured_at": "2026-07-13T09:50:10Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 47, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 324, "rating_method": "sequential_elo", "raw_elo": 1477.9429189179004, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.663482749304805, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 139, "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": "2026-07-13T04:36:42Z", "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": 48, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1477.3556932736828, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.595161332852324, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 120, "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": 30, "max_score": null, "measured_at": "2026-07-13T04:47:20Z", "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": 49, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1476.7933139751856, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.46552537742257, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 65, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 42, "draws": 51, "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": "2026-07-08T14:07:19Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 50, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1488.610341801933, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.928139079293686, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 21.344455490411935, "unilateral_faults": 7, "wins": 2 }, { "admitted_plugins": 3, "attempted_matches": 487, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 347, "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": 101, "max_score": null, "measured_at": "2026-07-13T10:26:31Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 51, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 487, "rating_method": "sequential_elo", "raw_elo": 1465.6068278537898, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.544748300487026, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 131, "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": "2026-07-13T10:04:50Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "DeepSeek V4 Flash", "model_slug": "deepseek-deepseek-v4-flash", "plugin_success_rate": null, "provider": "DeepSeek", "provider_key": "deepseek", "rank": 52, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1465.3767636306457, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.49964108257143, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 118, "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": 31, "max_score": null, "measured_at": "2026-07-13T05:16:33Z", "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": 53, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1463.709311867719, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.228985797353044, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 128, "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": 25, "max_score": null, "measured_at": "2026-07-13T04:54:59Z", "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": 54, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1463.6398360355618, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.200549099667672, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 120, "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": "2026-07-13T05:12:08Z", "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": 55, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1463.3688992933912, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.17036811395091, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 29, "max_score": null, "measured_at": "2026-07-13T06:16:19Z", "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": 56, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1446.0160640705587, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.182279312501247, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 3, "attempted_matches": 487, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 374, "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": 89, "max_score": null, "measured_at": "2026-07-13T10:00:13Z", "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": 57, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 487, "rating_method": "sequential_elo", "raw_elo": 1442.9088090480782, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 12.636240270675254, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 119, "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": "2026-07-13T05:57:35Z", "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": 58, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1440.8685316555038, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 12.29589482449053, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugins": 2, "attempted_matches": 324, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 162, "draws": 213, "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": 82, "max_score": null, "measured_at": "2026-07-13T10:40:55Z", "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": 59, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 324, "rating_method": "sequential_elo", "raw_elo": 1437.368264770207, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.676689633106054, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 2, "attempted_matches": 324, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 162, "draws": 126, "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": 129, "max_score": null, "measured_at": "2026-07-13T07:13:17Z", "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": 60, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 324, "rating_method": "sequential_elo", "raw_elo": 1437.0778401194718, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.62667967015868, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 69 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 65, "max_score": null, "measured_at": "2026-07-13T06:10:54Z", "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": 61, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1436.212990375402, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.494229241597468, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugins": 2, "attempted_matches": 324, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 162, "draws": 212, "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": 67, "max_score": null, "measured_at": "2026-07-13T10:36:29Z", "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": 324, "rating_method": "sequential_elo", "raw_elo": 1434.5762059507615, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.19590827465722, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 29, "max_score": null, "measured_at": "2026-07-13T05:58:01Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1434.2819346983647, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.16170917963443, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 121, "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": 32, "max_score": null, "measured_at": "2026-07-13T06:02:29Z", "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": 64, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1425.569778103603, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.661510668959371, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 127, "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": "2026-07-13T10:40:30Z", "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": 65, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1419.3287857720795, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 8.570363520623602, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 105, "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": "2026-07-13T06:34:38Z", "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": 66, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1415.212118591015, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 7.861489901697698, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:18:49Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 2197.6393105415173, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 188 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 5, "max_score": null, "measured_at": "2026-07-13T11:15:47Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 2105.624209097691, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 92.87168842486112, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 187 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:17:41Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 2015.7806124353233, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 85.91160100452133, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 173 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:17:33Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 2012.721991475772, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 85.67465290743922, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 176 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:14:29Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4", "model_slug": "gpt-5-4", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1975.6783507073544, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 82.80492164451171, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 171 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:14:22Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1969.2325757485887, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 82.30557434685794, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 169 }, { "admitted_plugins": 2, "attempted_matches": 384, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 192, "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": "2026-07-13T11:16:50Z", "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": 384, "rating_method": "sequential_elo", "raw_elo": 1952.804406401529, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 81.03290162382152, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 319 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:15:33Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 1950.2695886418971, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 80.83653200086476, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 164 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:17:54Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Sol", "model_slug": "gpt-5-6-sol", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1938.6627504861824, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 79.9373626528132, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 168 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:15:35Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1935.910063859551, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 79.72411496155975, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 168 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:18:09Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.5", "model_slug": "gpt-5-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1895.835343435012, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 76.61956919689428, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 163 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 36, "max_score": null, "measured_at": "2026-07-13T10:55:23Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1823.3793315826204, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 71.00647939020519, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 156 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:07:35Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1762.2764333304506, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 66.27290316140129, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 144 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:06:41Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1742.2509150779815, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 64.72154766303917, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 125 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T10:54:01Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Nemotron 3 Ultra 550B A55B", "model_slug": "nvidia-nemotron-3-ultra-550b-a55b", "plugin_success_rate": null, "provider": "NVIDIA", "provider_key": "nvidia", "rank": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1734.1724824403618, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 64.09572011977573, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 137 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 57, "max_score": null, "measured_at": "2026-07-13T10:52:12Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 1731.406709512891, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 63.88145864678119, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 135 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T10:52:14Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1730.7784959542173, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 63.83279161374329, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 134 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 61, "max_score": null, "measured_at": "2026-07-13T10:52:12Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1730.380099229294, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 63.80192824521784, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 131 }, { "admitted_plugins": 1, "attempted_matches": 193, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": 64, "max_score": null, "measured_at": "2026-07-13T10:52:13Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 193, "rating_method": "sequential_elo", "raw_elo": 1727.7505173272575, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 63.60397357250988, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 129 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T10:41:20Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 1701.8562513074885, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 61.59221622927624, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 138 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 72, "max_score": null, "measured_at": "2026-07-13T10:41:24Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1700.3153104058115, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 61.47284118437957, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 120 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T10:35:59Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 1695.2068025933097, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 61.07709054345052, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 124 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 64, "max_score": null, "measured_at": "2026-07-13T10:37:08Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "O3", "model_slug": "o3", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1684.1981360032778, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 60.22426090734482, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 128 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 63, "max_score": null, "measured_at": "2026-07-13T10:32:11Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1675.915942799595, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 59.58264825078116, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 129 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 80, "max_score": null, "measured_at": "2026-07-13T10:06:04Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1650.3489022497863, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 57.601996942098886, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 112 }, { "admitted_plugins": 2, "attempted_matches": 384, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 192, "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": 137, "max_score": null, "measured_at": "2026-07-13T10:58:23Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4 Mini", "model_slug": "gpt-5-4-mini", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 384, "rating_method": "sequential_elo", "raw_elo": 1643.207774355121, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 57.04878139560334, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 247 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 64, "max_score": null, "measured_at": "2026-07-13T09:53:57Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1643.0317640516944, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 57.03514606549368, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 128 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 81, "max_score": null, "measured_at": "2026-07-13T10:04:28Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Terra", "model_slug": "gpt-5-6-terra", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1615.8517000992508, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 54.92953555759788, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 111 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 74, "max_score": null, "measured_at": "2026-07-13T10:00:14Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1614.3851529159326, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 54.81592371456018, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 118 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 74, "max_score": null, "measured_at": "2026-07-13T10:00:40Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1609.8170186446755, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 54.462035234390775, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 118 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T09:47:56Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1607.776140994234, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 54.30393062383434, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 115 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T09:50:18Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1600.3588618520066, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 53.729321935304526, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 117 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 76, "max_score": null, "measured_at": "2026-07-13T09:55:11Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1595.0260967955364, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 53.3161983253421, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 116 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T09:23:11Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 1586.088462104333, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 52.623809317190414, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 123 }, { "admitted_plugins": 3, "attempted_matches": 585, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 293, "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": 233, "max_score": null, "measured_at": "2026-07-13T11:14:44Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GLM-5.2", "model_slug": "z-ai-glm-5-2", "plugin_success_rate": null, "provider": "Zhipu", "provider_key": "z-ai", "rank": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 581, "rating_method": "sequential_elo", "raw_elo": 1578.1127087882876, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 52.01544202340519, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 348 }, { "admitted_plugins": 1, "attempted_matches": 193, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": 79, "max_score": null, "measured_at": "2026-07-13T09:20:12Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 193, "rating_method": "sequential_elo", "raw_elo": 1576.6779912306322, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 51.90054642237549, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 114 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 70, "max_score": null, "measured_at": "2026-07-13T09:13:53Z", "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": 37, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1576.1321527703371, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 51.85250467308791, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 122 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 90, "max_score": null, "measured_at": "2026-07-13T09:30:30Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4", "model_slug": "gpt-5-4", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 38, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1566.0421009894353, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 51.07083914455005, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 102 }, { "admitted_plugins": 2, "attempted_matches": 217, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 112, "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": "2026-07-13T11:15:40Z", "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": 39, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 208, "rating_method": "sequential_elo", "raw_elo": 1605.5251211638574, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.95899109613581, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 47.46252452815364, "unilateral_faults": 5, "wins": 140 }, { "admitted_plugins": 1, "attempted_matches": 193, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": 84, "max_score": null, "measured_at": "2026-07-13T09:21:41Z", "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": 193, "rating_method": "sequential_elo", "raw_elo": 1560.6505408344633, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.65891696822854, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 109 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 102, "max_score": null, "measured_at": "2026-07-13T09:14:16Z", "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": 41, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1552.562062108092, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.02655493811615, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 90 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 101, "max_score": null, "measured_at": "2026-07-13T09:06:32Z", "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": 42, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1531.4907933302377, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 48.39418626411388, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 91 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 93, "max_score": null, "measured_at": "2026-07-13T08:50:28Z", "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": 43, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1509.421189981997, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 46.68447767783332, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 99 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 90, "max_score": null, "measured_at": "2026-07-13T08:44:34Z", "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": 44, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1491.417483801888, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 45.289749800068414, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 102 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 89, "max_score": null, "measured_at": "2026-07-13T08:30:02Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 1486.7510206741065, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.92824388846506, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 103 }, { "admitted_plugins": 1, "attempted_matches": 200, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 100, "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": 112, "max_score": null, "measured_at": "2026-07-13T11:00:20Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Nex N2 Pro", "model_slug": "nex-agi-nex-n2-pro", "plugin_success_rate": null, "provider": "Nex AGI", "provider_key": "nex-agi", "rank": 46, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 196, "rating_method": "sequential_elo", "raw_elo": 1479.8540775007548, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.416706220785926, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 84 }, { "admitted_plugins": 4, "attempted_matches": 595, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 302, "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": 319, "max_score": null, "measured_at": "2026-07-13T11:23:19Z", "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": 47, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 590, "rating_method": "sequential_elo", "raw_elo": 1491.5851365240233, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 43.714636706053675, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 23.73126226407682, "unilateral_faults": 5, "wins": 271 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 100, "max_score": null, "measured_at": "2026-07-13T08:24:30Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Step 3.7 Flash", "model_slug": "stepfun-step-3-7-flash", "plugin_success_rate": null, "provider": "StepFun", "provider_key": "stepfun", "rank": 48, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1464.0972635440774, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 43.17328153297657, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 92 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 112, "max_score": null, "measured_at": "2026-07-13T08:06:26Z", "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": 49, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1420.491315394543, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.79517533017037, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 2, "attempted_matches": 392, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 196, "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": 237, "max_score": null, "measured_at": "2026-07-13T11:03:25Z", "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": 50, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 388, "rating_method": "sequential_elo", "raw_elo": 1416.4311333710273, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.49201794250497, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 151 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 111, "max_score": null, "measured_at": "2026-07-13T08:00:20Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 1393.859774395402, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 37.73205830927727, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 81 }, { "admitted_plugins": 4, "attempted_matches": 779, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 391, "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": 466, "max_score": null, "measured_at": "2026-07-13T11:23:19Z", "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": 52, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 775, "rating_method": "sequential_elo", "raw_elo": 1385.1450491351493, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 37.06693423028597, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 309 }, { "admitted_plugins": 3, "attempted_matches": 402, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 205, "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": 238, "max_score": null, "measured_at": "2026-07-13T10:25:36Z", "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": 53, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 397, "rating_method": "sequential_elo", "raw_elo": 1409.8533137151826, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 36.85168878311291, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 31.64168301876909, "unilateral_faults": 5, "wins": 159 }, { "admitted_plugins": 2, "attempted_matches": 384, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 192, "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": 231, "max_score": null, "measured_at": "2026-07-13T10:59:39Z", "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": 54, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 384, "rating_method": "sequential_elo", "raw_elo": 1374.2089887589111, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 36.20973294620973, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 153 }, { "admitted_plugins": 3, "attempted_matches": 577, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 289, "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": 359, "max_score": null, "measured_at": "2026-07-13T11:18:27Z", "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": 55, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 577, "rating_method": "sequential_elo", "raw_elo": 1361.9867297938476, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 35.26480634810233, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 218 }, { "admitted_plugins": 2, "attempted_matches": 384, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 192, "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": 250, "max_score": null, "measured_at": "2026-07-13T09:47:56Z", "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": 384, "rating_method": "sequential_elo", "raw_elo": 1355.1696649798114, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.734776879783745, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 134 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 116, "max_score": null, "measured_at": "2026-07-13T08:20:21Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 1353.774056292458, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.62666056621864, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 76 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 135, "max_score": null, "measured_at": "2026-07-13T08:20:38Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 58, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1352.0043481632874, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.48956316868455, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 57 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 124, "max_score": null, "measured_at": "2026-07-13T08:46:31Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 1343.6234989865052, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 33.84030773931548, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 68 }, { "admitted_plugins": 3, "attempted_matches": 577, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 289, "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": 387, "max_score": null, "measured_at": "2026-07-13T11:17:38Z", "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": 60, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 577, "rating_method": "sequential_elo", "raw_elo": 1281.2970065683303, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 29.013859720451816, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 190 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 120, "max_score": null, "measured_at": "2026-07-13T09:11:14Z", "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": 61, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1279.2681339334554, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.85476638325884, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 72 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 133, "max_score": null, "measured_at": "2026-07-13T09:09:02Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5-Pro", "model_slug": "xiaomi-mimo-v2-5-pro", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 62, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1274.6569030680926, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.49753925600006, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 59 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 147, "max_score": null, "measured_at": "2026-07-13T10:00:53Z", "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": 63, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1215.9047396936294, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.94607194601389, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugins": 1, "attempted_matches": 193, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": 136, "max_score": null, "measured_at": "2026-07-13T10:08:37Z", "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": 64, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 193, "rating_method": "sequential_elo", "raw_elo": 1190.9592234534707, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 22.01932568848559, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 57 }, { "admitted_plugins": 3, "attempted_matches": 401, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 204, "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": 346, "max_score": null, "measured_at": "2026-07-13T11:07:07Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4 Nano", "model_slug": "gpt-5-4-nano", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 65, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 396, "rating_method": "sequential_elo", "raw_elo": 1199.8553628618754, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.581453206507906, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 31.64168301876909, "unilateral_faults": 5, "wins": 50 }, { "admitted_plugins": 2, "attempted_matches": 386, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 194, "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": 299, "max_score": null, "measured_at": "2026-07-13T11:18:49Z", "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": 66, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 386, "rating_method": "sequential_elo", "raw_elo": 1162.486027042327, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.813515423128983, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 87 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 157, "max_score": null, "measured_at": "2026-07-13T10:29:10Z", "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": 67, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1157.1332982965882, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.39311118822044, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 155, "max_score": null, "measured_at": "2026-07-13T10:25:36Z", "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": 68, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1149.9880919470363, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.839579688183345, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 3, "attempted_matches": 580, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 292, "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": 458, "max_score": null, "measured_at": "2026-07-13T11:18:02Z", "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": 69, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 580, "rating_method": "sequential_elo", "raw_elo": 1141.3473588954382, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.177778382565194, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 122 }, { "admitted_plugins": 1, "attempted_matches": 193, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": 160, "max_score": null, "measured_at": "2026-07-13T10:40:11Z", "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": 70, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 193, "rating_method": "sequential_elo", "raw_elo": 1125.827268341438, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.973622730477505, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 151, "max_score": null, "measured_at": "2026-07-13T10:39:33Z", "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": 71, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1111.2650370731944, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.839746009246886, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 165, "max_score": null, "measured_at": "2026-07-13T11:01:16Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Gemma 4 31B", "model_slug": "google-gemma-4-31b-it", "plugin_success_rate": null, "provider": "Google", "provider_key": "google", "rank": 72, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1078.2867553229037, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.28495376492924, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 164, "max_score": null, "measured_at": "2026-07-13T10:58:15Z", "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": 73, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 988.8038436102726, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 6.352808222192618, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 173, "max_score": null, "measured_at": "2026-07-13T10:55:25Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 981.3486241901296, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 5.775260340878278, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 181, "max_score": null, "measured_at": "2026-07-13T10:57:55Z", "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": 75, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 977.0384206037112, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 5.4413534752207235, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 183, "max_score": null, "measured_at": "2026-07-13T11:15:40Z", "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": 76, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 906.799250116218, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 0.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 5, "max_score": null, "measured_at": "2026-07-13T11:18:45Z", "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": 177, "rating_method": "sequential_elo", "raw_elo": 2113.172705854929, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 163 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 6, "max_score": null, "measured_at": "2026-07-13T11:18:53Z", "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": 177, "rating_method": "sequential_elo", "raw_elo": 2111.368816314729, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 99.85042729198668, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 162 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 16, "max_score": null, "measured_at": "2026-07-13T11:23:24Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 2053.838860363551, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 95.07321615577396, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 154 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 13, "max_score": null, "measured_at": "2026-07-13T11:18:24Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 2026.2525667066411, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 92.7858495768554, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 153 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": "2026-07-13T11:17:11Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 2021.3042300854584, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 92.37554944921584, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 152 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 22, "max_score": null, "measured_at": "2026-07-13T11:18:08Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 2013.227461625624, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 91.70584983423836, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 152 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 16, "max_score": null, "measured_at": "2026-07-13T11:17:43Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 2012.9222938793916, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 91.68054630806056, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 153 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 13, "max_score": null, "measured_at": "2026-07-13T11:16:01Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 2011.625745950398, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 91.5730407316453, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 151 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 15, "max_score": null, "measured_at": "2026-07-13T11:15:14Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1998.960307994121, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 90.52286342805895, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 159 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 14, "max_score": null, "measured_at": "2026-07-13T11:17:23Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1975.7342160431551, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 88.59703072475118, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 155 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 21, "max_score": null, "measured_at": "2026-07-13T11:14:59Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1958.6857036677432, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 87.18342301387884, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 151 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 20, "max_score": null, "measured_at": "2026-07-13T11:14:15Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Fable 5", "model_slug": "claude-fable-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1951.6074811596209, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 86.59651961160996, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 148 }, { "admitted_plugins": 1, "attempted_matches": 184, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 92, "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": 19, "max_score": null, "measured_at": "2026-07-13T11:18:54Z", "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": 180, "rating_method": "sequential_elo", "raw_elo": 1949.4731722166168, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 86.44725003634304, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 154 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 19, "max_score": null, "measured_at": "2026-07-13T11:17:13Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1946.3805267610455, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 86.16311739565705, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 143 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 33, "max_score": null, "measured_at": "2026-07-13T11:16:59Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1894.7354687831812, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 81.88087560362533, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 136 }, { "admitted_plugins": 2, "attempted_matches": 361, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 181, "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": 53, "max_score": null, "measured_at": "2026-07-13T11:18:18Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 357, "rating_method": "sequential_elo", "raw_elo": 1892.7238164979417, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 81.73143238427392, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 284 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": "2026-07-13T11:14:43Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4", "model_slug": "gpt-5-4", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 177, "rating_method": "sequential_elo", "raw_elo": 1842.2348648696632, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 77.53470726652617, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 134 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 42, "max_score": null, "measured_at": "2026-07-13T11:17:15Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1834.204736399648, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 76.86186232211922, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 129 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 34, "max_score": null, "measured_at": "2026-07-13T11:13:38Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1822.635273528246, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 75.9025597410182, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 129 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": "2026-07-13T11:15:05Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Luna", "model_slug": "gpt-5-6-luna", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1809.9810988197512, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 74.85331634964449, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 130 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 35, "max_score": null, "measured_at": "2026-07-13T11:17:14Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1800.8372467972556, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 74.09513760410667, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 140 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 37, "max_score": null, "measured_at": "2026-07-13T11:01:21Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT 5", "model_slug": "gpt-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1771.0027793472395, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 71.6213596985377, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 131 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 44, "max_score": null, "measured_at": "2026-07-13T11:05:20Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1762.1928177551893, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 70.89086607159972, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 130 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 63, "max_score": null, "measured_at": "2026-07-13T11:05:03Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Nemotron 3 Ultra 550B A55B", "model_slug": "nvidia-nemotron-3-ultra-550b-a55b", "plugin_success_rate": null, "provider": "NVIDIA", "provider_key": "nvidia", "rank": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1693.901124469253, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 65.22833892015394, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 106 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 15, "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": 61, "max_score": null, "measured_at": "2026-07-13T10:53:03Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1640.6007590549266, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 60.808844369375834, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 100 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 61, "max_score": null, "measured_at": "2026-07-13T10:52:13Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1639.345101131601, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 60.70472926047103, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 102 }, { "admitted_plugins": 2, "attempted_matches": 352, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 176, "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": 136, "max_score": null, "measured_at": "2026-07-13T11:17:35Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4 Mini", "model_slug": "gpt-5-4-mini", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 352, "rating_method": "sequential_elo", "raw_elo": 1620.0782625848524, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 59.10718509156764, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 202 }, { "admitted_plugins": 3, "attempted_matches": 529, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 265, "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": 236, "max_score": null, "measured_at": "2026-07-13T11:17:06Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 529, "rating_method": "sequential_elo", "raw_elo": 1581.298875583611, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 55.89406080232581, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 291 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 79, "max_score": null, "measured_at": "2026-07-13T10:28:56Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1580.6556232820392, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 55.8383868718608, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 92 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 72, "max_score": null, "measured_at": "2026-07-13T10:26:28Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 177, "rating_method": "sequential_elo", "raw_elo": 1578.273544793543, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 55.64788516644634, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 95 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 72, "max_score": null, "measured_at": "2026-07-13T10:04:33Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1555.0824415117218, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 53.71794104374275, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 90 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 73, "max_score": null, "measured_at": "2026-07-13T10:09:54Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 177, "rating_method": "sequential_elo", "raw_elo": 1543.393215932306, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 52.75572069190129, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 94 }, { "admitted_plugins": 4, "attempted_matches": 545, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 276, "draws": 16, "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": 222, "max_score": null, "measured_at": "2026-07-13T11:06:49Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4 Nano", "model_slug": "gpt-5-4-nano", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 540, "rating_method": "sequential_elo", "raw_elo": 1562.9244662084404, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 52.691719485250296, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 23.73126226407682, "unilateral_faults": 5, "wins": 302 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 83, "max_score": null, "measured_at": "2026-07-13T09:29:34Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1518.8008146816196, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.709585457011585, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 86 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 75, "max_score": null, "measured_at": "2026-07-13T09:54:41Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 177, "rating_method": "sequential_elo", "raw_elo": 1511.5014810101663, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.11136079666177, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 90 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 82, "max_score": null, "measured_at": "2026-07-13T09:50:45Z", "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": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 177, "rating_method": "sequential_elo", "raw_elo": 1510.6050308546082, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.03703003838767, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 85 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 74, "max_score": null, "measured_at": "2026-07-13T09:26:41Z", "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": 37, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 177, "rating_method": "sequential_elo", "raw_elo": 1510.0804882823834, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 49.99353665852848, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 95 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 78, "max_score": null, "measured_at": "2026-07-13T09:04:51Z", "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": 38, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 177, "rating_method": "sequential_elo", "raw_elo": 1501.6128850793782, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 49.29143028603119, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 88 }, { "admitted_plugins": 4, "attempted_matches": 555, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 282, "draws": 25, "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": 251, "max_score": null, "measured_at": "2026-07-13T11:13:03Z", "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": 39, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 546, "rating_method": "sequential_elo", "raw_elo": 1519.2247670718857, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 49.07869792911936, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 23.73126226407682, "unilateral_faults": 5, "wins": 270 }, { "admitted_plugins": 2, "attempted_matches": 193, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 100, "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": 82, "max_score": null, "measured_at": "2026-07-13T10:07:26Z", "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": 40, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1530.0774982969767, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 48.29169777153082, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 47.46252452815364, "unilateral_faults": 5, "wins": 94 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 83, "max_score": null, "measured_at": "2026-07-13T10:02:25Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 41, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1481.6018960616684, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 47.62517099084877, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 85 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 94, "max_score": null, "measured_at": "2026-07-13T10:25:36Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Sonnet 5", "model_slug": "claude-sonnet-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 42, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1438.558704040331, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.05616820620246, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 78 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 88, "max_score": null, "measured_at": "2026-07-13T10:36:21Z", "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": 43, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1386.8086718651762, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.765222291989005, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 77 }, { "admitted_plugins": 3, "attempted_matches": 530, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 266, "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": 325, "max_score": null, "measured_at": "2026-07-13T11:16:54Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 44, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 530, "rating_method": "sequential_elo", "raw_elo": 1383.0378483153977, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.45721318303368, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 202 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 106, "max_score": null, "measured_at": "2026-07-13T10:52:32Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5-Pro", "model_slug": "xiaomi-mimo-v2-5-pro", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 45, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1360.7970746059034, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 37.608424464229806, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 70 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 110, "max_score": null, "measured_at": "2026-07-13T10:53:27Z", "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": 46, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1327.686745679047, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.863022680785726, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 62 }, { "admitted_plugins": 1, "attempted_matches": 184, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 92, "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": 105, "max_score": null, "measured_at": "2026-07-13T11:23:24Z", "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": 47, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 180, "rating_method": "sequential_elo", "raw_elo": 1327.3034955719472, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.85894526176792, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 68 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 108, "max_score": null, "measured_at": "2026-07-13T11:02:44Z", "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": 48, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1326.1159042236277, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.73277356901328, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 65 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 121, "max_score": null, "measured_at": "2026-07-13T10:53:02Z", "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": 49, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1296.9997288863228, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 32.31855413088292, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 53 }, { "admitted_plugins": 3, "attempted_matches": 369, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 188, "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": 258, "max_score": null, "measured_at": "2026-07-13T11:18:07Z", "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": 50, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 364, "rating_method": "sequential_elo", "raw_elo": 1309.7151817493252, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 31.13760253997828, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 31.64168301876909, "unilateral_faults": 5, "wins": 99 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 114, "max_score": null, "measured_at": "2026-07-13T10:56:42Z", "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": 51, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1281.0925805566576, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 30.999584648874865, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 61 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 130, "max_score": null, "measured_at": "2026-07-13T10:57:22Z", "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": 52, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1253.9530728509649, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.749264121356106, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 113, "max_score": null, "measured_at": "2026-07-13T10:53:21Z", "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": 53, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1249.5659613788737, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.38549897464753, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 63 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 134, "max_score": null, "measured_at": "2026-07-13T10:57:42Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1225.2173017628277, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 26.36658657779288, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 127, "max_score": null, "measured_at": "2026-07-13T10:58:02Z", "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": 55, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1224.9666880119312, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 26.3458064931194, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 127, "max_score": null, "measured_at": "2026-07-13T11:18:17Z", "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": 56, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1215.569918034855, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.566656605763445, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 143, "max_score": null, "measured_at": "2026-07-13T11:14:06Z", "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": 57, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1185.296173265826, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.05645524038202, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 129, "max_score": null, "measured_at": "2026-07-13T11:16:31Z", "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": 58, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1175.1745877661265, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 22.21720598545791, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 137, "max_score": null, "measured_at": "2026-07-13T11:18:06Z", "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": 59, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1173.38593216378, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 22.0688964264832, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 145, "max_score": null, "measured_at": "2026-07-13T11:14:58Z", "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": 60, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1155.9492312898828, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.623101376173416, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 135, "max_score": null, "measured_at": "2026-07-13T11:16:25Z", "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": 61, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1155.29572221864, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.568914509783472, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 137, "max_score": null, "measured_at": "2026-07-13T11:13:11Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Gemma 4 31B", "model_slug": "google-gemma-4-31b-it", "plugin_success_rate": null, "provider": "Google", "provider_key": "google", "rank": 62, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1144.2132883540614, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.649994804578235, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 2, "attempted_matches": 352, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 176, "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": 286, "max_score": null, "measured_at": "2026-07-13T11:15:39Z", "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": 63, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 352, "rating_method": "sequential_elo", "raw_elo": 1141.355106683629, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.41300359036388, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 65 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 130, "max_score": null, "measured_at": "2026-07-13T11:14:05Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1133.2351915876884, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.739726395351543, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 131, "max_score": null, "measured_at": "2026-07-13T11:14:31Z", "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": 65, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1132.7350894614683, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.698259538520816, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 2, "attempted_matches": 355, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 179, "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": 291, "max_score": null, "measured_at": "2026-07-13T11:18:50Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "DeepSeek V4 Flash", "model_slug": "deepseek-deepseek-v4-flash", "plugin_success_rate": null, "provider": "DeepSeek", "provider_key": "deepseek", "rank": 66, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 355, "rating_method": "sequential_elo", "raw_elo": 1127.2314312945098, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.252344927225373, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 62 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 137, "max_score": null, "measured_at": "2026-07-13T11:18:03Z", "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": 67, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1104.7826259084304, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.380531331721865, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 149, "max_score": null, "measured_at": "2026-07-13T11:18:54Z", "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": 68, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1100.4204044235582, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.018829982550667, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 145, "max_score": null, "measured_at": "2026-07-13T11:17:55Z", "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": 69, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1098.618308520419, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.86940599714282, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 133, "max_score": null, "measured_at": "2026-07-13T11:14:54Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1091.291875403557, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.261921771004491, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 141, "max_score": null, "measured_at": "2026-07-13T11:16:43Z", "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": 71, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1074.5271388747817, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.87184383892639, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugins": 2, "attempted_matches": 354, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 178, "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": 301, "max_score": null, "measured_at": "2026-07-13T11:18:53Z", "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": 72, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 354, "rating_method": "sequential_elo", "raw_elo": 1059.1346381430687, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 12.60253042103812, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 52 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 143, "max_score": null, "measured_at": "2026-07-13T11:15:15Z", "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": 73, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1058.1316352827216, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 12.512381512184156, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugins": 1, "attempted_matches": 184, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 92, "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": 152, "max_score": null, "measured_at": "2026-07-13T11:18:45Z", "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": 74, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 180, "rating_method": "sequential_elo", "raw_elo": 1055.291266118791, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 12.304567698530732, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 168, "max_score": null, "measured_at": "2026-07-13T11:18:37Z", "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": 75, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 907.228743755124, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 0.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 3, "max_score": null, "measured_at": "2026-07-13T11:18:50Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 2162.280337984363, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 179 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 5, "max_score": null, "measured_at": "2026-07-13T11:18:50Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 2158.352458516296, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 99.70622072012152, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 177 }, { "admitted_plugins": 1, "attempted_matches": 183, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T11:18:43Z", "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": 183, "rating_method": "sequential_elo", "raw_elo": 1969.49620679625, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 85.5870460569821, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 159 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T11:16:50Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Fable 5", "model_slug": "claude-fable-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1953.181211186572, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 84.36077496947715, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 158 }, { "admitted_plugins": 2, "attempted_matches": 364, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 182, "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": "2026-07-13T11:18:55Z", "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": 364, "rating_method": "sequential_elo", "raw_elo": 1942.8740956603929, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 83.58987122827983, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 317 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T11:17:34Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1931.310445460898, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 82.72498704433467, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 155 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 29, "max_score": null, "measured_at": "2026-07-13T11:17:21Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1884.3584188699683, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 79.21328749427038, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 153 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T11:15:24Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Sol", "model_slug": "gpt-5-6-sol", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1877.1088979226424, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 78.67107150707326, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 148 }, { "admitted_plugins": 1, "attempted_matches": 190, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": 42, "max_score": null, "measured_at": "2026-07-13T11:18:28Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 184, "rating_method": "sequential_elo", "raw_elo": 1854.1131973283157, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 76.96313275824961, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 142 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 29, "max_score": null, "measured_at": "2026-07-13T11:14:02Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 1841.381570761984, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 75.99890487605245, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 153 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T11:17:05Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1837.7205673472693, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 75.72508615133052, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 148 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T11:14:17Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1831.9116897038568, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 75.29062070888055, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 142 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 54, "max_score": null, "measured_at": "2026-07-13T11:17:56Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1778.1423812549197, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 71.26903378287814, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 128 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T11:13:02Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1752.2710306808017, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 69.33402869859839, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 131 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T11:14:26Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1752.039738336122, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 69.31672956836447, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 132 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T11:15:11Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Qwen3.7 Max", "model_slug": "qwen-qwen3-7-max", "plugin_success_rate": null, "provider": "Alibaba", "provider_key": "qwen", "rank": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1738.410628244269, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 68.2973627113312, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 136 }, { "admitted_plugins": 1, "attempted_matches": 183, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T11:13:28Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT 5", "model_slug": "gpt-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 183, "rating_method": "sequential_elo", "raw_elo": 1735.7319944025955, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 68.10303654582466, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 132 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 54, "max_score": null, "measured_at": "2026-07-13T11:15:13Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Gemini 3.5 Flash", "model_slug": "google-gemini-3-5-flash", "plugin_success_rate": null, "provider": "Google", "provider_key": "google", "rank": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1732.245154505618, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 67.83622625086294, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 128 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T11:23:19Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1717.941915249386, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 66.76643901253581, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 136 }, { "admitted_plugins": 1, "attempted_matches": 183, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T11:02:36Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 183, "rating_method": "sequential_elo", "raw_elo": 1694.3564993288446, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 65.00842449211945, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 129 }, { "admitted_plugins": 3, "attempted_matches": 555, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 278, "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": 184, "max_score": null, "measured_at": "2026-07-13T11:17:36Z", "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": 549, "rating_method": "sequential_elo", "raw_elo": 1693.5342145811692, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 64.94690677132208, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 365 }, { "admitted_plugins": 3, "attempted_matches": 549, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 275, "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": 198, "max_score": null, "measured_at": "2026-07-13T11:17:00Z", "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": 544, "rating_method": "sequential_elo", "raw_elo": 1676.977850413982, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 63.69848733561735, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 346 }, { "admitted_plugins": 3, "attempted_matches": 390, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 199, "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": 102, "max_score": null, "measured_at": "2026-07-13T11:18:29Z", "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": 379, "rating_method": "sequential_elo", "raw_elo": 1703.0673274688045, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 63.63124555669186, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 31.64168301876909, "unilateral_faults": 5, "wins": 277 }, { "admitted_plugins": 2, "attempted_matches": 365, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 183, "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": 127, "max_score": null, "measured_at": "2026-07-13T11:14:44Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 365, "rating_method": "sequential_elo", "raw_elo": 1668.7527870423269, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 63.090428051106514, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 238 }, { "admitted_plugins": 1, "attempted_matches": 183, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T10:58:57Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 183, "rating_method": "sequential_elo", "raw_elo": 1668.6316311462508, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 63.084375317216946, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 119 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 65, "max_score": null, "measured_at": "2026-07-13T10:59:43Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 1668.553096042562, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 63.07248356950672, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 117 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T10:57:45Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 1663.0094819218623, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 62.65785807563824, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 119 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 72, "max_score": null, "measured_at": "2026-07-13T10:53:18Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1633.610606743942, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 60.45901759460469, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 110 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 84, "max_score": null, "measured_at": "2026-07-13T10:53:23Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1621.1705023347804, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 59.528580460612154, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 98 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 66, "max_score": null, "measured_at": "2026-07-13T11:04:15Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1621.1486703944136, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 59.526947576565824, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 116 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 73, "max_score": null, "measured_at": "2026-07-13T11:00:51Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1612.886056485539, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 58.90895896876939, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 109 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 72, "max_score": null, "measured_at": "2026-07-13T11:04:23Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1601.086003724768, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 58.0263934443509, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 110 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 80, "max_score": null, "measured_at": "2026-07-13T11:07:36Z", "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1590.4154432664634, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 57.228306437652854, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 102 }, { "admitted_plugins": 2, "attempted_matches": 364, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 182, "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": 168, "max_score": null, "measured_at": "2026-07-13T11:13:06Z", "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": 364, "rating_method": "sequential_elo", "raw_elo": 1581.3569640673556, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 56.55079239539596, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 196 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 82, "max_score": null, "measured_at": "2026-07-13T11:03:56Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1570.2651551058498, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 55.72119880023805, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 100 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 84, "max_score": null, "measured_at": "2026-07-13T10:30:54Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 1568.1544613440951, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 55.56333293433932, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 98 }, { "admitted_plugins": 1, "attempted_matches": 183, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T10:28:23Z", "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": 37, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 183, "rating_method": "sequential_elo", "raw_elo": 1560.8378514115036, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 55.02211698080321, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 105 }, { "admitted_plugins": 1, "attempted_matches": 183, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T10:36:53Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Sonnet 5", "model_slug": "claude-sonnet-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 38, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 183, "rating_method": "sequential_elo", "raw_elo": 1534.2555897441107, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 53.03394047139757, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 99 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 85, "max_score": null, "measured_at": "2026-07-13T10:40:14Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 1530.122360655427, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 52.71878456074053, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 97 }, { "admitted_plugins": 1, "attempted_matches": 172, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-12T07:19:59Z", "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": 168, "rating_method": "sequential_elo", "raw_elo": 1516.4605568504155, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 51.60719199001697, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 4, "wins": 80 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 100, "max_score": null, "measured_at": "2026-07-13T09:49:12Z", "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": 41, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1484.2995522204433, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 49.29154302405889, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 82 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 96, "max_score": null, "measured_at": "2026-07-13T09:53:58Z", "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": 42, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1482.8379416878386, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 49.18222426995193, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 86 }, { "admitted_plugins": 1, "attempted_matches": 172, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-12T07:19:31Z", "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": 43, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 168, "rating_method": "sequential_elo", "raw_elo": 1480.2852917577711, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 48.90152257863875, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 4, "wins": 78 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T10:02:47Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 44, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1474.3073791390875, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 48.54419488465525, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 78 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 108, "max_score": null, "measured_at": "2026-07-13T09:49:00Z", "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": 45, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1423.92500364893, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.775928034718326, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 74 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 106, "max_score": null, "measured_at": "2026-07-13T09:55:05Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Luna", "model_slug": "gpt-5-6-luna", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 46, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1413.788029156669, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.0177497121161, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 76 }, { "admitted_plugins": 3, "attempted_matches": 384, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 197, "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": 210, "max_score": null, "measured_at": "2026-07-13T10:41:05Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4 Mini", "model_slug": "gpt-5-4-mini", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 47, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 379, "rating_method": "sequential_elo", "raw_elo": 1428.2445475280326, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 43.17494898897335, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 29.960206985404067, "unilateral_faults": 5, "wins": 169 }, { "admitted_plugins": 2, "attempted_matches": 365, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 185, "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": 222, "max_score": null, "measured_at": "2026-07-13T11:06:32Z", "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": 48, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 365, "rating_method": "sequential_elo", "raw_elo": 1383.6457361670127, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 41.76631544139825, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 143 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 107, "max_score": null, "measured_at": "2026-07-13T09:48:51Z", "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": 49, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1381.410667501206, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 41.59613823731507, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 75 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 115, "max_score": null, "measured_at": "2026-07-13T09:56:36Z", "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": 50, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1379.2405515779446, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 41.433827988649966, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 67 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 118, "max_score": null, "measured_at": "2026-07-13T10:08:01Z", "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": 51, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1379.0615665243683, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 41.42044109616099, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 64 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 111, "max_score": null, "measured_at": "2026-07-13T10:08:31Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-OSS 120B", "model_slug": "openai-gpt-oss-120b", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 52, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1374.6495646773667, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 41.09045267977192, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 71 }, { "admitted_plugins": 2, "attempted_matches": 196, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 104, "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": 119, "max_score": null, "measured_at": "2026-07-13T09:58:18Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "DeepSeek V4 Flash", "model_slug": "deepseek-deepseek-v4-flash", "plugin_success_rate": null, "provider": "DeepSeek", "provider_key": "deepseek", "rank": 53, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 195, "rating_method": "sequential_elo", "raw_elo": 1408.585405788584, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 40.58862492867081, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 47.46252452815364, "unilateral_faults": 1, "wins": 76 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 128, "max_score": null, "measured_at": "2026-07-13T10:08:42Z", "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": 54, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1355.8473767548942, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.684173980817384, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 54 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 121, "max_score": null, "measured_at": "2026-07-13T10:26:05Z", "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": 55, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1350.700990355189, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.29925848053965, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 61 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 119, "max_score": null, "measured_at": "2026-07-13T10:26:40Z", "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": 56, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1341.347023577133, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 38.59964393116125, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 63 }, { "admitted_plugins": 3, "attempted_matches": 547, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 276, "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": 381, "max_score": null, "measured_at": "2026-07-13T11:18:55Z", "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": 57, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 547, "rating_method": "sequential_elo", "raw_elo": 1281.9524826632933, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.15933294953593, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 166 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 122, "max_score": null, "measured_at": "2026-07-13T10:52:56Z", "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": 58, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1273.086757806722, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 33.49422970310896, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 60 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 140, "max_score": null, "measured_at": "2026-07-13T11:06:38Z", "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": 59, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1262.3474980912197, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 32.691004448541584, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugins": 4, "attempted_matches": 564, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 287, "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": 389, "max_score": null, "measured_at": "2026-07-13T11:17:52Z", "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": 60, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 560, "rating_method": "sequential_elo", "raw_elo": 1263.3867857170294, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 31.250239151073856, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 23.73126226407682, "unilateral_faults": 4, "wins": 171 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 123, "max_score": null, "measured_at": "2026-07-13T11:02:13Z", "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": 61, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1231.8088563680926, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 30.40691700471232, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 59 }, { "admitted_plugins": 2, "attempted_matches": 364, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 184, "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": 261, "max_score": null, "measured_at": "2026-07-13T11:16:36Z", "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": 62, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 364, "rating_method": "sequential_elo", "raw_elo": 1210.7995576360236, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.83556108545949, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 103 }, { "admitted_plugins": 2, "attempted_matches": 365, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 183, "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": 283, "max_score": null, "measured_at": "2026-07-13T11:14:46Z", "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": 63, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 365, "rating_method": "sequential_elo", "raw_elo": 1206.821292633953, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.541022224441036, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 82 }, { "admitted_plugins": 1, "attempted_matches": 183, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 143, "max_score": null, "measured_at": "2026-07-13T11:02:13Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Grok Build 0.1", "model_slug": "x-ai-grok-build-0-1", "plugin_success_rate": null, "provider": "xAI", "provider_key": "x-ai", "rank": 64, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 183, "rating_method": "sequential_elo", "raw_elo": 1204.7719636992797, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.390754961728646, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 145, "max_score": null, "measured_at": "2026-07-13T10:56:09Z", "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": 65, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1172.978743544452, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 26.00681554513185, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 2, "attempted_matches": 370, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 185, "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": 288, "max_score": null, "measured_at": "2026-07-13T11:23:19Z", "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": 66, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 365, "rating_method": "sequential_elo", "raw_elo": 1159.9779010134412, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.03744784818577, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 77 }, { "admitted_plugins": 3, "attempted_matches": 382, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 195, "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": 335, "max_score": null, "measured_at": "2026-07-13T11:14:49Z", "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": 67, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 377, "rating_method": "sequential_elo", "raw_elo": 1153.88555576269, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 22.55210323620892, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 31.64168301876909, "unilateral_faults": 5, "wins": 42 }, { "admitted_plugins": 1, "attempted_matches": 183, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 154, "max_score": null, "measured_at": "2026-07-13T11:15:27Z", "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": 68, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 183, "rating_method": "sequential_elo", "raw_elo": 1073.1062106896916, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.54303167533976, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 163, "max_score": null, "measured_at": "2026-07-13T11:13:17Z", "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": 69, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1023.8789974673142, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.855145442036957, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 161, "max_score": null, "measured_at": "2026-07-13T11:13:55Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Luna", "model_slug": "gpt-5-6-luna", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 70, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1021.5883999199752, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.683823968600857, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 160, "max_score": null, "measured_at": "2026-07-13T11:15:38Z", "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": 71, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1019.0260887892624, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.492180124912394, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 170, "max_score": null, "measured_at": "2026-07-13T11:14:45Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Nemotron 3 Ultra 550B A55B", "model_slug": "nvidia-nemotron-3-ultra-550b-a55b", "plugin_success_rate": null, "provider": "NVIDIA", "provider_key": "nvidia", "rank": 72, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 969.4067666197518, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.780984592176267, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 168, "max_score": null, "measured_at": "2026-07-13T11:17:36Z", "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": 73, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 945.9132596935534, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.023826409826338, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 178, "max_score": null, "measured_at": "2026-07-13T11:18:28Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 825.2631495386737, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 0.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "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": "2026-07-13T11:18:07Z", "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": 189, "rating_method": "sequential_elo", "raw_elo": 2132.1542218237096, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 98.16260901359112, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 184 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-08", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T11:13:02Z", "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": 189, "rating_method": "sequential_elo", "raw_elo": 2028.7089535272355, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 87.01781118744486, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 176 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-08", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T11:07:15Z", "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": 189, "rating_method": "sequential_elo", "raw_elo": 1972.1744321291676, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 80.92699793368016, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 168 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-08", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T11:04:20Z", "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": 189, "rating_method": "sequential_elo", "raw_elo": 1970.0641033155896, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 80.6996391732329, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 178 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 19, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 19, "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": "2026-07-13T11:06:22Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1953.4202094748457, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 78.8982296737467, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 154 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 14, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "draws": 14, "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": "2026-07-13T11:06:34Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1947.083957209489, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 78.21558607258677, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 154 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 8, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 8, "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": "2026-07-13T11:06:38Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1919.2682873054955, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 75.22709210395418, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 162 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-08", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T11:01:31Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1882.6097202931392, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 71.27763820744504, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 162 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 9, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "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": 29, "max_score": null, "measured_at": "2026-07-13T10:32:11Z", "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": 188, "rating_method": "sequential_elo", "raw_elo": 1802.4501299122312, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 62.633290327266224, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 150 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 21, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "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": "2026-07-13T10:25:36Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1767.1268182403671, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 58.83595172966278, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 142 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 64, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 64, "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": "2026-07-13T10:41:27Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.5", "model_slug": "gpt-5-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1747.3200463010708, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 56.70204582476052, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 113 }, { "admitted_plugins": 3, "attempted_matches": 567, "capped_draws": 138, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 284, "draws": 138, "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": 102, "max_score": null, "measured_at": "2026-07-13T11:04:54Z", "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": 565, "rating_method": "sequential_elo", "raw_elo": 1736.33042286224, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 55.512559137757854, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 325 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 25, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "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": 52, "max_score": null, "measured_at": "2026-07-13T10:48:42Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1722.1576383809518, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 53.99114416916196, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 112 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 35, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 35, "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": "2026-07-13T09:23:48Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1686.9911699498823, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.194183278796665, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 114 }, { "admitted_plugins": 3, "attempted_matches": 562, "capped_draws": 258, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 282, "draws": 258, "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": 99, "max_score": null, "measured_at": "2026-07-13T11:18:54Z", "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": 562, "rating_method": "sequential_elo", "raw_elo": 1646.9348350260022, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 45.87307214409487, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 205 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 32, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "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": 36, "max_score": null, "measured_at": "2026-07-13T09:24:44Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1625.9873576107975, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 43.621865701208215, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 120 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 52, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "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": 41, "max_score": null, "measured_at": "2026-07-13T09:15:36Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1588.1145511719858, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.541594289860214, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 95 }, { "admitted_plugins": 2, "attempted_matches": 377, "capped_draws": 140, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 190, "draws": 140, "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": 82, "max_score": null, "measured_at": "2026-07-13T11:06:04Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 377, "rating_method": "sequential_elo", "raw_elo": 1576.8230098237732, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 38.32915139307305, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 155 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 89, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "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": 27, "max_score": null, "measured_at": "2026-07-13T10:37:03Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1552.067087925525, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 35.64126006400562, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 70 }, { "admitted_plugins": 3, "attempted_matches": 561, "capped_draws": 219, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 281, "draws": 219, "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": 161, "max_score": null, "measured_at": "2026-07-13T11:14:33Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 561, "rating_method": "sequential_elo", "raw_elo": 1534.1212585814792, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 33.71621527419026, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 181 }, { "admitted_plugins": 3, "attempted_matches": 567, "capped_draws": 195, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 284, "draws": 195, "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": 194, "max_score": null, "measured_at": "2026-07-13T11:17:36Z", "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": 564, "rating_method": "sequential_elo", "raw_elo": 1525.4849294334806, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 32.79405211184169, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 175 }, { "admitted_plugins": 1, "attempted_matches": 190, "capped_draws": 76, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "draws": 76, "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": "2026-07-13T09:18:44Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 190, "rating_method": "sequential_elo", "raw_elo": 1523.3706998722455, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 32.58279423932358, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 75 }, { "admitted_plugins": 1, "attempted_matches": 190, "capped_draws": 101, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "draws": 101, "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": 42, "max_score": null, "measured_at": "2026-07-13T09:47:56Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1508.2797586658528, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 30.948758875345156, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 1, "wins": 46 }, { "admitted_plugins": 1, "attempted_matches": 89, "capped_draws": 23, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 53, "draws": 23, "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": "2026-07-12T07:18:18Z", "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": 83, "rating_method": "sequential_elo", "raw_elo": 1515.3168846424774, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 30.131321176688537, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 10.804472558998102, "unilateral_faults": 6, "wins": 22 }, { "admitted_plugins": 4, "attempted_matches": 750, "capped_draws": 402, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 377, "draws": 402, "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": 177, "max_score": null, "measured_at": "2026-07-13T11:16:43Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 750, "rating_method": "sequential_elo", "raw_elo": 1495.6559371907333, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 29.57626057477822, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 171 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 121, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 121, "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": "2026-07-13T11:05:14Z", "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": 188, "rating_method": "sequential_elo", "raw_elo": 1488.6466607664197, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.825303955669103, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 107, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 107, "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": "2026-07-13T11:05:29Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1485.3601398335422, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.454508438462973, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 1, "attempted_matches": 190, "capped_draws": 79, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 64, "max_score": null, "measured_at": "2026-07-13T09:49:11Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 190, "rating_method": "sequential_elo", "raw_elo": 1480.5657308160917, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 27.971150478895108, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 151, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 151, "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": "2026-07-13T10:58:26Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1459.1719015817816, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.633087743778862, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 114, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 114, "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": "2026-07-13T11:05:58Z", "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1447.9378811498193, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 24.422777320201146, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 1, "attempted_matches": 190, "capped_draws": 58, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 73, "max_score": null, "measured_at": "2026-07-13T10:26:59Z", "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": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 190, "rating_method": "sequential_elo", "raw_elo": 1441.216892792548, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.731857066176303, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 59 }, { "admitted_plugins": 3, "attempted_matches": 563, "capped_draws": 346, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 283, "draws": 346, "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": 137, "max_score": null, "measured_at": "2026-07-13T11:13:29Z", "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 563, "rating_method": "sequential_elo", "raw_elo": 1438.9778296664265, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.471310902314137, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 138, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 138, "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": "2026-07-13T10:58:04Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.5", "model_slug": "gpt-5-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1435.5146429235408, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.084345116795618, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 152, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 152, "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": 34, "max_score": null, "measured_at": "2026-07-13T10:57:06Z", "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": 186, "rating_method": "sequential_elo", "raw_elo": 1416.9867323704073, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 21.088218849678245, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 124, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 124, "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": "2026-07-13T10:56:19Z", "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": 35, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1413.7250064681264, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.753531281042477, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 128, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 128, "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": 43, "max_score": null, "measured_at": "2026-07-13T11:02:14Z", "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": 36, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1412.9108924569598, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.649103435748216, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 145, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "draws": 145, "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": 43, "max_score": null, "measured_at": "2026-07-13T11:07:45Z", "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": 37, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1409.8911668433243, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.348748045283045, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 136, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 136, "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": 43, "max_score": null, "measured_at": "2026-07-13T11:07:38Z", "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": 38, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1407.0770575585177, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.020588361400733, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 127, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 127, "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": 45, "max_score": null, "measured_at": "2026-07-13T11:07:08Z", "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": 39, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1407.0276642403533, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.01526691408883, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 132, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 132, "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": "2026-07-13T10:37:05Z", "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": 40, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1405.431006653321, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.868227433674654, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 127, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 127, "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": 45, "max_score": null, "measured_at": "2026-07-13T11:06:28Z", "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": 186, "rating_method": "sequential_elo", "raw_elo": 1404.395730339692, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.73171241519593, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 3, "attempted_matches": 561, "capped_draws": 360, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 282, "draws": 360, "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": 153, "max_score": null, "measured_at": "2026-07-13T11:17:23Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4 Mini", "model_slug": "gpt-5-4-mini", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 42, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 561, "rating_method": "sequential_elo", "raw_elo": 1402.7777329451226, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.565765832701924, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugins": 1, "attempted_matches": 187, "capped_draws": 109, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "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": 55, "max_score": null, "measured_at": "2026-07-13T11:02:32Z", "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": 43, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1402.0270488022595, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.476519719735425, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 129, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "draws": 129, "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": "2026-07-13T11:03:10Z", "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": 44, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1395.871357285086, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.83830734885763, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 132, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "draws": 132, "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": 49, "max_score": null, "measured_at": "2026-07-13T11:06:10Z", "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": 45, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1391.8628989274982, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.40645136621559, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 132, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 132, "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": 45, "max_score": null, "measured_at": "2026-07-13T11:15:41Z", "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": 46, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1391.1774857786118, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.32434758125932, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 2, "attempted_matches": 375, "capped_draws": 191, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 188, "draws": 191, "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": 138, "max_score": null, "measured_at": "2026-07-13T11:07:46Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 47, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 375, "rating_method": "sequential_elo", "raw_elo": 1388.505901557898, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.032358403988177, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 129, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "draws": 129, "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": 51, "max_score": null, "measured_at": "2026-07-13T11:15:55Z", "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": 48, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1387.7628352400186, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 17.96472617545748, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 129, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 129, "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": "2026-07-13T11:16:26Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Minimax M3", "model_slug": "minimax-minimax-m3", "plugin_success_rate": null, "provider": "MiniMax", "provider_key": "minimax", "rank": 49, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1386.9649746432217, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 17.85378941887912, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 2, "attempted_matches": 381, "capped_draws": 256, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 192, "draws": 256, "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": 99, "max_score": null, "measured_at": "2026-07-13T11:16:33Z", "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": 50, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 378, "rating_method": "sequential_elo", "raw_elo": 1383.6671916058622, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 17.523477184350448, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 3, "attempted_matches": 402, "capped_draws": 248, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 208, "draws": 248, "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": 105, "max_score": null, "measured_at": "2026-07-13T11:18:39Z", "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": 394, "rating_method": "sequential_elo", "raw_elo": 1404.027846907638, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 17.458145034751666, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 23.65262231176029, "unilateral_faults": 5, "wins": 41 }, { "admitted_plugins": 1, "attempted_matches": 187, "capped_draws": 132, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "draws": 132, "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": "2026-07-13T11:14:46Z", "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": 52, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 187, "rating_method": "sequential_elo", "raw_elo": 1383.0665226852393, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 17.44217760975673, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 127, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 127, "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": "2026-07-13T11:16:21Z", "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": 53, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1380.5556298457757, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 17.163271107680195, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 2, "attempted_matches": 375, "capped_draws": 247, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 189, "draws": 247, "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": 110, "max_score": null, "measured_at": "2026-07-13T11:15:19Z", "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": 54, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 375, "rating_method": "sequential_elo", "raw_elo": 1379.838515181817, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 17.098567323610556, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 126, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 126, "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": 47, "max_score": null, "measured_at": "2026-07-13T11:14:14Z", "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": 55, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1377.5527713035483, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.839754605623078, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 127, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 127, "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": 53, "max_score": null, "measured_at": "2026-07-13T11:17:51Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Gemini 3.1 Flash Lite", "model_slug": "google-gemini-3-1-flash-lite", "plugin_success_rate": null, "provider": "Google", "provider_key": "google", "rank": 56, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1376.104841957335, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.683760232020177, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 187, "capped_draws": 131, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "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": 46, "max_score": null, "measured_at": "2026-07-13T11:13:38Z", "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": 187, "rating_method": "sequential_elo", "raw_elo": 1375.233252453259, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.598251014653428, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 129, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 129, "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": 49, "max_score": null, "measured_at": "2026-07-13T11:15:22Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Gemma 4 31B", "model_slug": "google-gemma-4-31b-it", "plugin_success_rate": null, "provider": "Google", "provider_key": "google", "rank": 58, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1372.120747480266, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.25452912074359, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 129, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 129, "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": 49, "max_score": null, "measured_at": "2026-07-13T11:17:20Z", "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": 59, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1370.494322139764, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.079304270948928, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 115, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 115, "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": 66, "max_score": null, "measured_at": "2026-07-13T11:18:07Z", "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": 60, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1369.61060669953, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.984096147083603, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 3, "attempted_matches": 400, "capped_draws": 238, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 208, "draws": 238, "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": 131, "max_score": null, "measured_at": "2026-07-13T11:18:54Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "DeepSeek V4 Flash", "model_slug": "deepseek-deepseek-v4-flash", "plugin_success_rate": null, "provider": "DeepSeek", "provider_key": "deepseek", "rank": 61, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 394, "rating_method": "sequential_elo", "raw_elo": 1387.6906144268287, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.85333826777108, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 21.786315039332067, "unilateral_faults": 6, "wins": 25 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 126, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 126, "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": 60, "max_score": null, "measured_at": "2026-07-13T11:13:55Z", "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": 62, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1365.3921680716376, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.52961769268853, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 127, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "draws": 127, "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": 51, "max_score": null, "measured_at": "2026-07-13T11:00:06Z", "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": 63, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1363.4289818338318, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.33482982433031, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 127, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 127, "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": "2026-07-13T11:13:11Z", "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": 64, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1360.7459680636564, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.029053862157538, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 1, "attempted_matches": 187, "capped_draws": 132, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "draws": 132, "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": 47, "max_score": null, "measured_at": "2026-07-13T11:17:07Z", "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": 65, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 187, "rating_method": "sequential_elo", "raw_elo": 1356.976545254924, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.6313431604106, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 133, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 133, "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": 52, "max_score": null, "measured_at": "2026-07-13T11:15:45Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 66, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1355.3864631081572, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.451641282917274, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 125, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "draws": 125, "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": 57, "max_score": null, "measured_at": "2026-07-13T10:52:12Z", "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": 67, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1348.3105677082017, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.706029670811375, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 128, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 128, "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": 58, "max_score": null, "measured_at": "2026-07-13T11:15:30Z", "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": 68, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1344.363634400764, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.264083848544765, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 2, "attempted_matches": 375, "capped_draws": 239, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 189, "draws": 239, "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": 132, "max_score": null, "measured_at": "2026-07-13T11:14:55Z", "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": 69, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 375, "rating_method": "sequential_elo", "raw_elo": 1329.1473511389008, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.6372950572833, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 190, "capped_draws": 130, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 130, "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": 56, "max_score": null, "measured_at": "2026-07-13T11:04:16Z", "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": 189, "rating_method": "sequential_elo", "raw_elo": 1327.0295869443844, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.421558133782472, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 118, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 118, "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": 64, "max_score": null, "measured_at": "2026-07-13T11:16:04Z", "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": 71, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1324.8868169932389, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.1824442971418, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 105, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 105, "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": 81, "max_score": null, "measured_at": "2026-07-13T11:17:43Z", "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": 72, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1272.3937366442383, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 5.510322141763682, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 25, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "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": 123, "max_score": null, "measured_at": "2026-07-13T11:15:51Z", "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": 73, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1256.275063394386, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 3.7904762066821025, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 1, "attempted_matches": 37, "capped_draws": 5, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 36, "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": "2026-07-08T14:06:51Z", "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": 74, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1276.2559408675754, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/mixed" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 1.9931136856735752, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/mixed", "track_name": "Reasoning Variants", "uncertainty": 38.449493652678655, "unilateral_faults": 1, "wins": 1 }, { "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-2026-07-12": 19 }, "run_count": 16, "token_priced_attempt_count": 19, "total": 16.69817 }, "codegen_evaluated_cells": 16, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-05T07:10:10Z", "losses": null, "max_score": 100.0, "measured_at": null, "min_score": 0.0, "model_code_failure_rate": 0.0625, "model_code_failures": 1, "model_display_name": "Claude Fable 5", "model_slug": "claude-fable-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1855.5663996282271, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 3, "repaired_rate": 0.1875, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 71.76351812060925, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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-2026-07-12": 28 }, "run_count": 24, "token_priced_attempt_count": 28, "total": 25.878315000000004 }, "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": "2026-07-05T05:45:18Z", "losses": null, "max_score": 100.0, "measured_at": null, "min_score": 13.62877706153271, "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": 1717.9229137475622, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 4, "repaired_rate": 0.16666666666666666, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 55.03108007981919, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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-2026-07-12": 27 }, "run_count": 26, "token_priced_attempt_count": 27, "total": 85.66335500000001 }, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T18:48:15Z", "losses": null, "max_score": 100.0, "measured_at": null, "min_score": 3.7904762066821025, "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": 1694.417138364542, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 1, "repaired_rate": 0.038461538461538464, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 54.48673126722695, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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-2026-07-12": 25 }, "run_count": 24, "token_priced_attempt_count": 25, "total": 10.456240000000005 }, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-05T12:55:25Z", "losses": null, "max_score": 91.70584983423836, "measured_at": null, "min_score": 8.792181774741303, "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1653.8479474508551, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 1, "repaired_rate": 0.041666666666666664, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 51.11429918736825, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": 16, "cost_basis_counts": { "local_standard_estimate": 16 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 6, "max": 0.072978, "mean": 0.047875499999999994, "median": 0.046959, "min": 0.03731, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 16 }, "run_count": 16, "token_priced_attempt_count": 16, "total": 0.7660079999999999 }, "codegen_evaluated_cells": 16, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 10, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04" ], "first_pass_admitted": 10, "first_pass_rate": 0.625, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "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": "2026-07-05T07:07:37Z", "losses": null, "max_score": 75.22709210395418, "measured_at": null, "min_score": 21.69121170153766, "model_code_failure_rate": 0.375, "model_code_failures": 6, "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": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1580.818924642047, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 49.84964254354767, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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-2026-07-12": 26 }, "run_count": 24, "token_priced_attempt_count": 26, "total": 26.566349999999996 }, "codegen_evaluated_cells": 24, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 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": "2026-07-05T05:29:38Z", "losses": null, "max_score": 99.70622072012152, "measured_at": null, "min_score": 7.861489901697698, "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1625.357329710935, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 1, "repaired_rate": 0.041666666666666664, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 48.86806366335861, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": 14, "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": "2026-07-05T08:30:36Z", "losses": null, "max_score": 92.37554944921584, "measured_at": null, "min_score": 5.510322141763682, "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1654.11061579364, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 14, "repaired_rate": 0.875, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 44.54265821122643, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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-2026-07-12": 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": 15, "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": "2026-07-05T06:26:09Z", "losses": null, "max_score": 82.30557434685794, "measured_at": null, "min_score": 14.519546549031492, "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1548.5168154960263, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 3, "repaired_rate": 0.1875, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 42.30722155664184, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": 24, "cost_basis_counts": { "local_list_price_estimate": 25 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 1, "max": 0.3825, "mean": 0.21125, "median": 0.22746, "min": 0.09594, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 25 }, "run_count": 24, "token_priced_attempt_count": 25, "total": 5.07 }, "codegen_evaluated_cells": 24, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 23, "failed_game_aliases": [ "GB2-03" ], "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": "2026-07-05T07:16:13Z", "losses": null, "max_score": 78.8982296737467, "measured_at": null, "min_score": 9.13197672529834, "model_code_failure_rate": 0.041666666666666664, "model_code_failures": 1, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1562.084983827698, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 1, "repaired_rate": 0.041666666666666664, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 41.85732695118905, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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-2026-07-12": 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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T16:11:38Z", "losses": null, "max_score": 79.72411496155975, "measured_at": null, "min_score": 10.94878978246065, "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1551.8912162872678, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 7, "repaired_rate": 0.28, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 40.914723362521215, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": "2026-07-04T19:21:35Z", "losses": null, "max_score": 85.67465290743922, "measured_at": null, "min_score": 10.124210580685428, "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1522.9349340807007, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 8, "repaired_rate": 0.5, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 39.81549926362298, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": 24, "cost_basis_counts": { "local_list_price_estimate": 25 }, "evidence_basis": "Standard list-price estimate", "failed_cell_count": 1, "max": 0.4567, "mean": 0.16913741666666668, "median": 0.074902, "min": 0.049788, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 25 }, "run_count": 24, "token_priced_attempt_count": 25, "total": 4.059298 }, "codegen_evaluated_cells": 24, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 23, "failed_game_aliases": [ "GB2-03" ], "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": "2026-07-05T07:15:25Z", "losses": null, "max_score": 70.32957472930792, "measured_at": null, "min_score": 9.95306063713581, "model_code_failure_rate": 0.041666666666666664, "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1548.557308019611, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 1, "repaired_rate": 0.041666666666666664, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 39.80405395327182, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": 6, "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": "2026-07-05T12:55:25Z", "losses": null, "max_score": 59.58264825078116, "measured_at": null, "min_score": 12.540709613495318, "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1585.2125254234652, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 39.1856023679816, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": 1.2846227783999995 }, "codegen_evaluated_cells": 15, "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" ], "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": "2026-07-05T10:32:44Z", "losses": null, "max_score": 70.89086607159972, "measured_at": null, "min_score": 0.0, "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1473.8012575894222, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 8, "repaired_rate": 0.5333333333333333, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 36.799297276606374, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 62, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 62, "cell_count": 24, "cost_basis_counts": { "local_list_price_estimate": 1, "provider_reported": 155 }, "evidence_basis": "Mixed: Provider-reported + Standard list-price estimate", "failed_cell_count": 19, "max": 0.25823185294999995, "mean": 0.1184507759284722, "median": 0.12954777533333334, "min": 0.0140238704, "recorded_attempt_count": 155, "run_count": 81, "token_priced_attempt_count": 1, "total": 8.920653839 }, "codegen_evaluated_cells": 81, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 62, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "GB2-05", "GB2-06", "GB2-07", "GB2-08" ], "first_pass_admitted": 20, "first_pass_rate": 0.24691358024691357, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_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": "2026-07-05T07:41:02Z", "losses": null, "max_score": 64.94690677132208, "measured_at": null, "min_score": 10.660343551755462, "model_code_failure_rate": 0.2345679012345679, "model_code_failures": 19, "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": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1558.196265954019, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 42, "repaired_rate": 0.5185185185185185, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 36.64105747370666, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": { "local_standard_estimate": 11 }, "evidence_basis": "Standard list-price estimate", "max": 0.094594, "mean": 0.0571955, "median": 0.043012, "min": 0.032534, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 11 }, "run_count": 8, "token_priced_attempt_count": 11, "total": 0.4575640000000001 }, "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": 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": "2026-07-04T18:57:57Z", "losses": null, "max_score": 58.420430590270925, "measured_at": null, "min_score": 9.661510668959371, "model_code_failure_rate": 0.0, "model_code_failures": 0, "model_display_name": "GPT 4.1", "model_slug": "gpt-4-1", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1487.1654241857807, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 36.54444523651211, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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-2026-07-12": 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": [ "GB2-03" ], "infra_failures_excluded": 1, "is_recent_addition": false, "last_measured_at": "2026-07-05T06:30:08Z", "losses": null, "max_score": 83.58987122827983, "measured_at": null, "min_score": 9.599170646265678, "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1490.8630876287768, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 8, "repaired_rate": 0.13333333333333333, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 35.28518178122639, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": 14, "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": "2026-07-05T09:55:26Z", "losses": null, "max_score": 79.21328749427038, "measured_at": null, "min_score": 10.794214509222783, "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1500.9339883323885, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 6, "repaired_rate": 0.375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 34.8956181223097, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": 0.025206018750000003, "min": 0.0058062875, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 130 }, "run_count": 81, "token_priced_attempt_count": 130, "total": 6.1442372999999995 }, "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": [ "GB2-05" ], "infra_failures_excluded": 1, "is_recent_addition": false, "last_measured_at": "2026-07-05T06:44:52Z", "losses": null, "max_score": 95.07321615577396, "measured_at": null, "min_score": 8.830356337516129, "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1482.436272781935, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 32, "repaired_rate": 0.3950617283950617, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 34.047267912775915, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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-2026-07-12": 28 }, "run_count": 26, "token_priced_attempt_count": 28, "total": 29.297331000000007 }, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T18:48:15Z", "losses": null, "max_score": 86.16311739565705, "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1495.2994016176078, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 2, "repaired_rate": 0.07692307692307693, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 32.26455248473879, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": 0.4852846 }, "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": 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": "2026-07-05T11:04:02Z", "losses": null, "max_score": 61.07709054345052, "measured_at": null, "min_score": 11.56683145120459, "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1426.6853726769298, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 8, "repaired_rate": 1.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 31.658220453712367, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": 13, "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": "2026-07-05T10:45:41Z", "losses": null, "max_score": 60.293433204479186, "measured_at": null, "min_score": 5.4413534752207235, "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1407.5626946678449, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 9, "repaired_rate": 0.5625, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 29.062873594987224, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": 12, "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": "2026-07-05T10:04:29Z", "losses": null, "max_score": 81.88087560362533, "measured_at": null, "min_score": 9.082592792115568, "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1421.9431998298592, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 7, "repaired_rate": 0.4117647058823529, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 29.008853440121953, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": 25 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.007539278, "mean": 0.0022565913437500003, "median": 0.0014932259999999998, "min": 0.00090937, "recorded_attempt_count": 25, "run_count": 17, "total": 0.04172561300000001 }, "codegen_evaluated_cells": 17, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 13, "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": "2026-07-04T19:32:07Z", "losses": null, "max_score": 78.86564479729775, "measured_at": null, "min_score": 3.928336942357347, "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1463.5546150912244, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 4, "repaired_rate": 0.2352941176470588, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 28.58787229523722, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 37, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 37, "cell_count": 24, "cost_basis_counts": { "provider_reported": 104 }, "evidence_basis": "Provider-reported", "failed_cell_count": 16, "max": 0.0597184625, "mean": 0.016139657731944448, "median": 0.014928570933333331, "min": 0.00169122, "recorded_attempt_count": 104, "run_count": 53, "total": 0.7042121472 }, "codegen_evaluated_cells": 53, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 37, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "GB2-05", "GB2-06", "GB2-07", "GB2-08" ], "first_pass_admitted": 13, "first_pass_rate": 0.24528301886792453, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_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" ], "infra_failures_excluded": 1, "is_recent_addition": false, "last_measured_at": "2026-07-05T10:40:42Z", "losses": null, "max_score": 52.75572069190129, "measured_at": null, "min_score": 11.587783971795917, "model_code_failure_rate": 0.3018867924528302, "model_code_failures": 16, "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": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1398.4339285828007, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 24, "repaired_rate": 0.4528301886792453, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 27.709511117240464, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 21, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 21, "cell_count": 24, "cost_basis_counts": { "provider_reported": 70 }, "evidence_basis": "Provider-reported", "failed_cell_count": 13, "max": 0.13485595, "mean": 0.03294963020833333, "median": 0.02851355, "min": 0.0111232, "recorded_attempt_count": 70, "run_count": 34, "total": 1.2116408500000002 }, "codegen_evaluated_cells": 34, "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", "GB2-05", "GB2-06", "GB2-07" ], "first_pass_admitted": 7, "first_pass_rate": 0.2058823529411765, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_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": "2026-07-05T11:04:02Z", "losses": null, "max_score": 65.22833892015394, "measured_at": null, "min_score": 8.373533192314857, "model_code_failure_rate": 0.38235294117647056, "model_code_failures": 13, "model_display_name": "Nemotron 3 Ultra 550B A55B", "model_slug": "nvidia-nemotron-3-ultra-550b-a55b", "plugin_success_rate": null, "provider": "NVIDIA", "provider_key": "nvidia", "rank": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1407.5999824033777, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 14, "repaired_rate": 0.4117647058823529, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 25.743639790694644, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": 10, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-05T01:47:28Z", "losses": null, "max_score": 54.462035234390775, "measured_at": null, "min_score": 13.28495376492924, "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1329.8060672176732, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 5, "repaired_rate": 0.35714285714285715, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 24.555774968914633, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 9, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 9, "cell_count": 16, "cost_basis_counts": { "provider_reported": 39 }, "evidence_basis": "Provider-reported", "failed_cell_count": 7, "max": 0.1121957, "mean": 0.0500512375, "median": 0.0441228, "min": 0.02174195, "recorded_attempt_count": 39, "run_count": 16, "total": 0.8008198 }, "codegen_evaluated_cells": 16, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 9, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "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": "2026-07-05T01:47:40Z", "losses": null, "max_score": 50.02655493811615, "measured_at": null, "min_score": 7.242946177185584, "model_code_failure_rate": 0.4375, "model_code_failures": 7, "model_display_name": "Step 3.7 Flash", "model_slug": "stepfun-step-3-7-flash", "plugin_success_rate": null, "provider": "StepFun", "provider_key": "stepfun", "rank": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1360.3123311877314, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 9, "repaired_rate": 0.5625, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 24.114539618643047, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 44, "attempted_matches": 0, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 44, "cell_count": 24, "cost_basis_counts": { "provider_reported": 86 }, "evidence_basis": "Provider-reported", "failed_cell_count": 11, "max": 0.017371817999999997, "mean": 0.005185113858472222, "median": 0.0029930771, "min": 0.001825724, "recorded_attempt_count": 86, "run_count": 55, "total": 0.25255216964 }, "codegen_evaluated_cells": 55, "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": 29, "first_pass_rate": 0.5272727272727272, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_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": "2026-07-05T05:51:59Z", "losses": null, "max_score": 63.090428051106514, "measured_at": null, "min_score": 6.7491967108184525, "model_code_failure_rate": 0.2, "model_code_failures": 11, "model_display_name": "DeepSeek V4 Flash", "model_slug": "deepseek-deepseek-v4-flash", "plugin_success_rate": null, "provider": "DeepSeek", "provider_key": "deepseek", "rank": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1385.5962543465794, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 15, "repaired_rate": 0.2727272727272727, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 23.526214420463003, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": 35 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.01660212, "mean": 0.0056431221249999995, "median": 0.0034032865, "min": 0.001130258, "recorded_attempt_count": 35, "run_count": 16, "total": 0.09028995400000002 }, "codegen_evaluated_cells": 16, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 12, "failed_game_aliases": [ "GB2-01", "GB2-03", "GB2-05", "GB2-07" ], "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": "2026-07-05T10:59:49Z", "losses": null, "max_score": 76.86186232211922, "measured_at": null, "min_score": 0.034968617309127016, "model_code_failure_rate": 0.25, "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": 30, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1414.5776956126392, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 11, "repaired_rate": 0.6875, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 23.460569708462337, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": 50 }, "evidence_basis": "Provider-reported", "failed_cell_count": 8, "max": 0.0422995, "mean": 0.014503875, "median": 0.010566625, "min": 0.003432, "recorded_attempt_count": 50, "run_count": 24, "total": 0.34809300000000004 }, "codegen_evaluated_cells": 24, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 16, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "GB2-08" ], "first_pass_admitted": 5, "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": "2026-07-05T08:46:15Z", "losses": null, "max_score": 51.60719199001697, "measured_at": null, "min_score": 0.0, "model_code_failure_rate": 0.3333333333333333, "model_code_failures": 8, "model_display_name": "Gemini 3.1 Flash Lite", "model_slug": "google-gemini-3-1-flash-lite", "plugin_success_rate": null, "provider": "Google", "provider_key": "google", "rank": 31, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1283.5686840211083, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 11, "repaired_rate": 0.4583333333333333, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 17.029973727530717, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": 53 }, "evidence_basis": "Provider-reported", "failed_cell_count": 12, "max": 0.215758025, "mean": 0.132049078125, "median": 0.1281735, "min": 0.061553, "recorded_attempt_count": 53, "run_count": 24, "total": 3.4057992500000003 }, "codegen_evaluated_cells": 24, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 12, "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": "2026-07-05T01:47:44Z", "losses": null, "max_score": 76.96313275824961, "measured_at": null, "min_score": 1.9931136856735752, "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": 32, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1398.30865299702, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 12, "repaired_rate": 0.5, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 26.4529107505613, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": 45 }, "evidence_basis": "Provider-reported", "failed_cell_count": 13, "max": 0.0, "mean": 0.0, "median": 0.0, "min": 0.0, "recorded_attempt_count": 45, "run_count": 24, "total": 0.0 }, "codegen_evaluated_cells": 24, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 11, "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": "2026-07-05T01:47:43Z", "losses": null, "max_score": 46.68447767783332, "measured_at": null, "min_score": 13.87184383892639, "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": 33, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1349.704709633552, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 5, "repaired_rate": 0.20833333333333337, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 22.726936500186973, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "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": 28 }, "evidence_basis": "Provider-reported", "failed_cell_count": 9, "max": 0.3927285, "mean": 0.116635875, "median": 0.0747585, "min": 0.0223935, "recorded_attempt_count": 28, "run_count": 17, "total": 2.2589025 }, "codegen_evaluated_cells": 17, "conditional_success_score": null, "contributing_entrants": null, "distinct_rated_opponents": 0, "draws": null, "entry_count": 8, "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": "2026-07-04T19:37:24Z", "losses": null, "max_score": 25.41066276207961, "measured_at": null, "min_score": 10.992113891672274, "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": 34, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 0, "rating_method": "sequential_elo", "raw_elo": 1183.8867708116463, "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": { "requested_effort": "aggregate", "source": "public_redacted_snapshot", "track_id": "overall" }, "provider_route": "unknown_legacy", "reasoning_bucket": "aggregate", "reasoning_bucket_label": "Aggregate of public reasoning variants", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": null }, "repaired_admitted": 4, "repaired_rate": 0.2352941176470588, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 15.328325362371965, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "overall", "track_name": "Overall Models", "uncertainty": null, "unilateral_faults": 0, "wins": null }, { "admitted_plugins": 8, "attempted_matches": 1251, "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-2026-07-12": 11 }, "run_count": 8, "token_priced_attempt_count": 11, "total": 12.66097 }, "codegen_evaluated_cells": 8, "conditional_success_score": 73.67927701948544, "contributing_entrants": null, "distinct_rated_opponents": 626, "draws": 100, "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": "2026-07-13T11:18:24Z", "losses": 84, "max_score": 100.0, "measured_at": null, "min_score": 0.0, "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": 1245, "rating_method": "sequential_elo", "raw_elo": 1895.921266284868, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 73.67927701948544, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 6, "wins": 1061 }, { "admitted_plugins": 8, "attempted_matches": 1273, "capped_draws": 25, "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-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 80.47395 }, "codegen_evaluated_cells": 8, "conditional_success_score": 72.38492380259433, "contributing_entrants": null, "distinct_rated_opponents": 636, "draws": 117, "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": "2026-07-13T11:17:54Z", "losses": 232, "max_score": 100.0, "measured_at": null, "min_score": 3.7904762066821025, "model_code_failure_rate": 0.0, "model_code_failures": 0, "model_display_name": "GPT-5.6 Sol", "model_slug": "gpt-5-6-sol", "plugin_success_rate": 1.0, "provider": "OpenAI", "provider_key": "openai", "rank": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1260, "rating_method": "sequential_elo", "raw_elo": 1780.9955276529745, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 72.38492380259433, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 1, "wins": 911 }, { "admitted_plugins": 7, "attempted_matches": 1245, "capped_draws": 21, "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-2026-07-12": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 7.44989 }, "codegen_evaluated_cells": 8, "conditional_success_score": 70.89694035940671, "contributing_entrants": null, "distinct_rated_opponents": 626, "draws": 156, "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": "2026-07-13T11:18:43Z", "losses": 173, "max_score": 90.52286342805895, "measured_at": null, "min_score": 51.90054642237549, "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1245, "rating_method": "sequential_elo", "raw_elo": 1827.9186952521943, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 68.56926691137262, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 0, "wins": 916 }, { "admitted_plugins": 7, "attempted_matches": 1131, "capped_draws": 104, "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-2026-07-12": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 21.885475 }, "codegen_evaluated_cells": 8, "conditional_success_score": 69.89301893844359, "contributing_entrants": null, "distinct_rated_opponents": 570, "draws": 237, "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": "2026-07-13T11:18:50Z", "losses": 117, "max_score": 99.70622072012152, "measured_at": null, "min_score": 7.861489901697698, "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": 1118, "rating_method": "sequential_elo", "raw_elo": 1804.4068332428672, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 67.5983060275447, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 0, "wins": 764 }, { "admitted_plugins": 8, "attempted_matches": 1271, "capped_draws": 36, "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-2026-07-12": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 21.140645 }, "codegen_evaluated_cells": 8, "conditional_success_score": 66.72404359849178, "contributing_entrants": null, "distinct_rated_opponents": 636, "draws": 232, "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": "2026-07-13T11:18:53Z", "losses": 79, "max_score": 100.0, "measured_at": null, "min_score": 20.816680906992, "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1256, "rating_method": "sequential_elo", "raw_elo": 1865.1994334603448, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 66.72404359849178, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 3, "wins": 945 }, { "admitted_plugins": 8, "attempted_matches": 1247, "capped_draws": 9, "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-2026-07-12": 10 }, "run_count": 9, "token_priced_attempt_count": 10, "total": 28.806541000000003 }, "codegen_evaluated_cells": 9, "conditional_success_score": 56.611113304620986, "contributing_entrants": null, "distinct_rated_opponents": 623, "draws": 273, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:17:34Z", "losses": 197, "max_score": 86.16311739565705, "measured_at": null, "min_score": 9.920800162399148, "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1242, "rating_method": "sequential_elo", "raw_elo": 1711.794849262461, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 1, "repaired_rate": 0.1111111111111111, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 54.96845939316894, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 3, "wins": 772 }, { "admitted_plugins": 8, "attempted_matches": 1248, "capped_draws": 70, "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-2026-07-12": 11 }, "run_count": 8, "token_priced_attempt_count": 11, "total": 65.3280125 }, "codegen_evaluated_cells": 8, "conditional_success_score": 51.831196830812125, "contributing_entrants": null, "distinct_rated_opponents": 625, "draws": 282, "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": "2026-07-13T16:11:38Z", "losses": 228, "max_score": 79.72411496155975, "measured_at": null, "min_score": 28.075303957431895, "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1244, "rating_method": "sequential_elo", "raw_elo": 1665.4419312545165, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 51.831196830812125, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 3, "wins": 734 }, { "admitted_plugins": 12, "attempted_matches": 2143, "capped_draws": 152, "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-2026-07-12": 15 }, "run_count": 12, "token_priced_attempt_count": 15, "total": 12.214044 }, "codegen_evaluated_cells": 12, "conditional_success_score": 47.56517919446139, "contributing_entrants": null, "distinct_rated_opponents": 1074, "draws": 575, "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": [ "GB2-03" ], "infra_failures_excluded": 1, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:18:55Z", "losses": 506, "max_score": 83.58987122827983, "measured_at": null, "min_score": 15.497093457640895, "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 2143, "rating_method": "sequential_elo", "raw_elo": 1631.4087552697572, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 2, "repaired_rate": 0.16666666666666666, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 47.56517919446139, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 0, "wins": 1062 }, { "admitted_plugins": 15, "attempted_matches": 2513, "capped_draws": 354, "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-2026-07-12": 25 }, "run_count": 17, "token_priced_attempt_count": 25, "total": 5.07700365 }, "codegen_evaluated_cells": 17, "conditional_success_score": 47.00678735360725, "contributing_entrants": null, "distinct_rated_opponents": 1260, "draws": 775, "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": [ "GB2-05" ], "infra_failures_excluded": 1, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:23:24Z", "losses": 726, "max_score": 95.07321615577396, "measured_at": null, "min_score": 11.62667967015868, "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 2508, "rating_method": "sequential_elo", "raw_elo": 1605.9317071471346, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 5, "repaired_rate": 0.29411764705882354, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 45.55868236667957, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 1, "wins": 1007 }, { "admitted_plugins": 8, "attempted_matches": 1260, "capped_draws": 139, "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-2026-07-12": 10 }, "run_count": 8, "token_priced_attempt_count": 10, "total": 2.2561124999999995 }, "codegen_evaluated_cells": 8, "conditional_success_score": 44.44751572350101, "contributing_entrants": null, "distinct_rated_opponents": 635, "draws": 416, "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": "2026-07-13T18:48:15Z", "losses": 291, "max_score": 82.30557434685794, "measured_at": null, "min_score": 14.519546549031492, "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1255, "rating_method": "sequential_elo", "raw_elo": 1594.464728220512, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 44.44751572350101, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 3, "wins": 548 }, { "admitted_plugins": 8, "attempted_matches": 1265, "capped_draws": 139, "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": 0.4567, "mean": 0.3681425, "median": 0.355077, "min": 0.234622, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 2.945139999999999 }, "codegen_evaluated_cells": 8, "conditional_success_score": 43.91806233006658, "contributing_entrants": null, "distinct_rated_opponents": 636, "draws": 398, "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": "2026-07-13T14:18:39Z", "losses": 297, "max_score": 70.32957472930792, "measured_at": null, "min_score": 20.849828926322857, "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1254, "rating_method": "sequential_elo", "raw_elo": 1592.154001226328, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 43.91806233006658, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 5, "wins": 559 }, { "admitted_plugins": 7, "attempted_matches": 1243, "capped_draws": 67, "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": 0.3825, "mean": 0.27230375, "median": 0.25636749999999997, "min": 0.236235, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 2.17843 }, "codegen_evaluated_cells": 8, "conditional_success_score": 43.846531385589635, "contributing_entrants": null, "distinct_rated_opponents": 623, "draws": 349, "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": "2026-07-13T11:16:56Z", "losses": 363, "max_score": 71.27763820744504, "measured_at": null, "min_score": 13.244643810555974, "model_code_failure_rate": 0.125, "model_code_failures": 1, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": 0.875, "provider": "Anthropic", "provider_key": "anthropic", "rank": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1243, "rating_method": "sequential_elo", "raw_elo": 1582.3827248107011, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 42.40697128077773, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 0, "wins": 531 }, { "admitted_plugins": 6, "attempted_matches": 1076, "capped_draws": 156, "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": 45.42604803979628, "contributing_entrants": null, "distinct_rated_opponents": 538, "draws": 265, "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": "2026-07-13T11:17:33Z", "losses": 341, "max_score": 85.67465290743922, "measured_at": null, "min_score": 15.029053862157538, "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": 1075, "rating_method": "sequential_elo", "raw_elo": 1574.876009512716, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 42.273701035639824, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 0, "wins": 469 }, { "admitted_plugins": 6, "attempted_matches": 914, "capped_draws": 105, "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": 41.71617219774557, "contributing_entrants": null, "distinct_rated_opponents": 454, "draws": 170, "entry_count": 6, "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": "2026-07-13T18:14:57Z", "losses": 291, "max_score": 88.59703072475118, "measured_at": null, "min_score": 5.510322141763682, "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 903, "rating_method": "sequential_elo", "raw_elo": 1590.1553819546964, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 38.82127255036194, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 10, "wins": 442 }, { "admitted_plugins": 18, "attempted_matches": 3070, "capped_draws": 400, "codegen_cost_usd": { "admitted_cell_count": 18, "cell_count": 8, "cost_basis_counts": { "provider_reported": 55 }, "evidence_basis": "Provider-reported", "failed_cell_count": 7, "max": 0.25823185294999995, "mean": 0.20731004458333335, "median": 0.20662718916666667, "min": 0.13654539825, "recorded_attempt_count": 55, "run_count": 25, "total": 5.1714206112 }, "codegen_evaluated_cells": 25, "conditional_success_score": 40.104186114581104, "contributing_entrants": null, "distinct_rated_opponents": 1537, "draws": 1042, "entry_count": 18, "failed_game_aliases": [ "GB2-01", "GB2-03", "GB2-04", "GB2-06" ], "first_pass_admitted": 1, "first_pass_rate": 0.04, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_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": "2026-07-13T11:18:54Z", "losses": 826, "max_score": 64.94690677132208, "measured_at": null, "min_score": 10.660343551755462, "model_code_failure_rate": 0.28, "model_code_failures": 7, "model_display_name": "GLM-5.2", "model_slug": "z-ai-glm-5-2", "plugin_success_rate": 0.72, "provider": "Zhipu", "provider_key": "z-ai", "rank": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 3046, "rating_method": "sequential_elo", "raw_elo": 1577.7018814752237, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 17, "repaired_rate": 0.68, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 36.94220646382741, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 4, "wins": 1178 }, { "admitted_plugins": 7, "attempted_matches": 1244, "capped_draws": 79, "codegen_cost_usd": { "admitted_cell_count": 7, "cell_count": 8, "cost_basis_counts": { "provider_reported": 14 }, "evidence_basis": "Provider-reported", "failed_cell_count": 2, "max": 0.007539278, "mean": 0.0032457859375, "median": 0.001956843, "min": 0.001266762, "recorded_attempt_count": 14, "run_count": 9, "total": 0.03158643900000001 }, "codegen_evaluated_cells": 9, "conditional_success_score": 30.442194068979944, "contributing_entrants": null, "distinct_rated_opponents": 623, "draws": 359, "entry_count": 7, "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": "2026-07-13T11:15:51Z", "losses": 465, "max_score": 65.10038689956093, "measured_at": null, "min_score": 8.215126650850651, "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1243, "rating_method": "sequential_elo", "raw_elo": 1493.0824790183017, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 2, "repaired_rate": 0.2222222222222222, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 28.58839887541176, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 0, "wins": 419 }, { "admitted_plugins": 11, "attempted_matches": 1966, "capped_draws": 202, "codegen_cost_usd": { "admitted_cell_count": 11, "cell_count": 8, "cost_basis_counts": { "provider_reported": 28 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.017371817999999997, "mean": 0.010146428355, "median": 0.010218342, "min": 0.003562685, "recorded_attempt_count": 28, "run_count": 15, "total": 0.14822491768 }, "codegen_evaluated_cells": 15, "conditional_success_score": 30.22734971003966, "contributing_entrants": null, "distinct_rated_opponents": 984, "draws": 494, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:17:20Z", "losses": 888, "max_score": 63.090428051106514, "measured_at": null, "min_score": 9.719984864483806, "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1966, "rating_method": "sequential_elo", "raw_elo": 1407.371129112015, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 6, "repaired_rate": 0.4, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 27.972122858189454, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 0, "wins": 584 }, { "admitted_plugins": 5, "attempted_matches": 872, "capped_draws": 131, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 19 }, "evidence_basis": "Provider-reported", "failed_cell_count": 3, "max": 0.01660212, "mean": 0.008820586750000001, "median": 0.0070236809999999995, "min": 0.00271606, "recorded_attempt_count": 19, "run_count": 8, "total": 0.070564694 }, "codegen_evaluated_cells": 8, "conditional_success_score": 31.118210871946445, "contributing_entrants": null, "distinct_rated_opponents": 437, "draws": 396, "entry_count": 5, "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": "2026-07-13T11:17:15Z", "losses": 247, "max_score": 76.86186232211922, "measured_at": null, "min_score": 7.858209030686404, "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 871, "rating_method": "sequential_elo", "raw_elo": 1498.009740982813, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 27.668436835415857, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 0, "wins": 228 }, { "admitted_plugins": 5, "attempted_matches": 912, "capped_draws": 149, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 20 }, "evidence_basis": "Provider-reported", "failed_cell_count": 3, "max": 0.1121957, "mean": 0.0607572625, "median": 0.060057275, "min": 0.02174195, "recorded_attempt_count": 20, "run_count": 8, "total": 0.4860581000000001 }, "codegen_evaluated_cells": 8, "conditional_success_score": 29.12946837211943, "contributing_entrants": null, "distinct_rated_opponents": 456, "draws": 153, "entry_count": 5, "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": "2026-07-13T11:07:38Z", "losses": 524, "max_score": 50.02655493811615, "measured_at": null, "min_score": 7.242946177185584, "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 912, "rating_method": "sequential_elo", "raw_elo": 1324.2847423940473, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 25.90016691576, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 0, "wins": 235 }, { "admitted_plugins": 5, "attempted_matches": 864, "capped_draws": 208, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 19 }, "evidence_basis": "Provider-reported", "failed_cell_count": 3, "max": 0.0597184625, "mean": 0.02467013555, "median": 0.0239011175, "min": 0.0040410944, "recorded_attempt_count": 19, "run_count": 8, "total": 0.1973610844 }, "codegen_evaluated_cells": 8, "conditional_success_score": 24.89745288066118, "contributing_entrants": null, "distinct_rated_opponents": 433, "draws": 487, "entry_count": 5, "failed_game_aliases": [ "GB2-03", "GB2-05", "GB2-07" ], "first_pass_admitted": 0, "first_pass_rate": 0.0, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:15:45Z", "losses": 255, "max_score": 52.75572069190129, "measured_at": null, "min_score": 11.587783971795917, "model_code_failure_rate": 0.375, "model_code_failures": 3, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": 0.625, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 864, "rating_method": "sequential_elo", "raw_elo": 1423.5079074524867, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 22.13731391004702, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 0, "wins": 122 }, { "admitted_plugins": 5, "attempted_matches": 890, "capped_draws": 127, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 19 }, "evidence_basis": "Provider-reported", "failed_cell_count": 3, "max": 0.0422995, "mean": 0.027492531250000004, "median": 0.025548, "min": 0.0204145, "recorded_attempt_count": 19, "run_count": 8, "total": 0.21994025 }, "codegen_evaluated_cells": 8, "conditional_success_score": 24.39763717968764, "contributing_entrants": null, "distinct_rated_opponents": 445, "draws": 266, "entry_count": 5, "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": "2026-07-13T11:17:51Z", "losses": 450, "max_score": 51.60719199001697, "measured_at": null, "min_score": 6.352808222192618, "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 886, "rating_method": "sequential_elo", "raw_elo": 1322.5356017085342, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 21.69290792511931, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 4, "wins": 170 }, { "admitted_plugins": 9, "attempted_matches": 1629, "capped_draws": 298, "codegen_cost_usd": { "admitted_cell_count": 9, "cell_count": 8, "cost_basis_counts": { "provider_reported": 35 }, "evidence_basis": "Provider-reported", "failed_cell_count": 7, "max": 0.045691600000000006, "mean": 0.031545040625, "median": 0.035551075, "min": 0.01864685, "recorded_attempt_count": 35, "run_count": 16, "total": 0.5047206500000001 }, "codegen_evaluated_cells": 16, "conditional_success_score": 21.796342773056757, "contributing_entrants": null, "distinct_rated_opponents": 816, "draws": 729, "entry_count": 9, "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": "2026-07-13T11:23:24Z", "losses": 600, "max_score": 39.49201794250497, "measured_at": null, "min_score": 8.373533192314857, "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1614, "rating_method": "sequential_elo", "raw_elo": 1390.9004043024624, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 7, "repaired_rate": 0.4375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 18.87618655106051, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 0, "wins": 285 }, { "admitted_plugins": 4, "attempted_matches": 739, "capped_draws": 8, "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-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 0.375032 }, "codegen_evaluated_cells": 8, "conditional_success_score": 67.76558792775211, "contributing_entrants": null, "distinct_rated_opponents": 370, "draws": 19, "entry_count": 4, "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": 8, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:06:38Z", "losses": 256, "max_score": 75.22709210395418, "measured_at": null, "min_score": 39.765222291989005, "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": 739, "rating_method": "sequential_elo", "raw_elo": 1630.099363957344, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 56.98383996600714, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 0, "wins": 464 }, { "admitted_plugins": 4, "attempted_matches": 727, "capped_draws": 32, "codegen_cost_usd": { "admitted_cell_count": 4, "cell_count": 8, "cost_basis_counts": { "provider_reported": 14 }, "evidence_basis": "Provider-reported", "failed_cell_count": 5, "max": 0.3927285, "mean": 0.1902770625, "median": 0.16804049999999998, "min": 0.08751, "recorded_attempt_count": 14, "run_count": 9, "total": 1.914945 }, "codegen_evaluated_cells": 9, "conditional_success_score": 18.526079722299833, "contributing_entrants": null, "distinct_rated_opponents": 364, "draws": 32, "entry_count": 4, "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": "2026-07-13T11:15:27Z", "losses": 577, "max_score": 23.94607194601389, "measured_at": null, "min_score": 10.992113891672274, "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": 727, "rating_method": "sequential_elo", "raw_elo": 1137.825653118707, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": 2, "repaired_rate": 0.2222222222222222, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 15.12648075125229, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": null, "unilateral_faults": 0, "wins": 118 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 0, "max_score": null, "measured_at": "2026-07-13T11:18:36Z", "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": 177, "rating_method": "sequential_elo", "raw_elo": 2182.455891497867, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 177 }, { "admitted_plugins": 1, "attempted_matches": 180, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 87, "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": "2026-07-13T11:17:35Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 174, "rating_method": "sequential_elo", "raw_elo": 1925.7488185883976, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 78.74765662668415, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 158 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 19, "max_score": null, "measured_at": "2026-07-13T11:16:04Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Luna", "model_slug": "gpt-5-6-luna", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1902.5784711158203, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 76.84550196312736, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 157 }, { "admitted_plugins": 1, "attempted_matches": 178, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-01", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T11:17:45Z", "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": 178, "rating_method": "sequential_elo", "raw_elo": 1895.8385074190176, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 76.30199821690978, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 153 }, { "admitted_plugins": 1, "attempted_matches": 178, "capped_draws": 25, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 90, "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": 26, "max_score": null, "measured_at": "2026-07-13T11:18:11Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Sonnet 5", "model_slug": "claude-sonnet-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 178, "rating_method": "sequential_elo", "raw_elo": 1823.6256878798372, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 70.32957472930792, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 127 }, { "admitted_plugins": 1, "attempted_matches": 178, "capped_draws": 40, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 40, "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": "2026-07-13T11:15:33Z", "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": 175, "rating_method": "sequential_elo", "raw_elo": 1809.797470834809, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 69.16491509843954, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 126 }, { "admitted_plugins": 1, "attempted_matches": 178, "capped_draws": 21, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 90, "draws": 21, "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": "2026-07-13T11:16:56Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 178, "rating_method": "sequential_elo", "raw_elo": 1782.8143637430246, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 66.95423898711903, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 125 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 21, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 21, "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": 36, "max_score": null, "measured_at": "2026-07-13T11:15:51Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Hy3 Preview", "model_slug": "tencent-hy3-preview", "plugin_success_rate": null, "provider": "Tencent", "provider_key": "tencent", "rank": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1760.5677988463635, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 65.10038689956093, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 119 }, { "admitted_plugins": 1, "attempted_matches": 178, "capped_draws": 12, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 90, "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": 57, "max_score": null, "measured_at": "2026-07-13T10:52:12Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 178, "rating_method": "sequential_elo", "raw_elo": 1608.2690654622086, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 52.518319634361845, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 109 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 29, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 71, "max_score": null, "measured_at": "2026-07-13T10:37:56Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1566.477261696739, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 49.04796171811881, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 76 }, { "admitted_plugins": 2, "attempted_matches": 356, "capped_draws": 204, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 178, "draws": 204, "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": "2026-07-13T11:07:31Z", "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": 354, "rating_method": "sequential_elo", "raw_elo": 1506.5009951955217, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.09453827805331, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 65 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 30, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 70, "max_score": null, "measured_at": "2026-07-13T09:59:28Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT 5", "model_slug": "gpt-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1454.819819377688, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.8132367021536, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 76 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 38, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 80, "max_score": null, "measured_at": "2026-07-13T09:49:22Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Terra", "model_slug": "gpt-5-6-terra", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1439.664792003006, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 38.55982709946261, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugins": 2, "attempted_matches": 353, "capped_draws": 73, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 177, "draws": 73, "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": 171, "max_score": null, "measured_at": "2026-07-13T10:08:24Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 353, "rating_method": "sequential_elo", "raw_elo": 1418.9687991737023, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 36.85164453712511, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 109 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 67, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 67, "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": 90, "max_score": null, "measured_at": "2026-07-13T11:16:56Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1336.2354430799348, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 30.005613640447077, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugins": 1, "attempted_matches": 184, "capped_draws": 42, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 92, "draws": 42, "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": 105, "max_score": null, "measured_at": "2026-07-13T11:18:01Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Nemotron 3 Ultra 550B A55B", "model_slug": "nvidia-nemotron-3-ultra-550b-a55b", "plugin_success_rate": null, "provider": "NVIDIA", "provider_key": "nvidia", "rank": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 180, "rating_method": "sequential_elo", "raw_elo": 1335.819638015444, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 29.998854107361183, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 2, "attempted_matches": 353, "capped_draws": 96, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 177, "draws": 96, "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": 216, "max_score": null, "measured_at": "2026-07-13T11:13:02Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4 Nano", "model_slug": "gpt-5-4-nano", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 353, "rating_method": "sequential_elo", "raw_elo": 1286.6750551799234, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.910176402612787, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 75, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "draws": 75, "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": 100, "max_score": null, "measured_at": "2026-07-13T10:53:33Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 177, "rating_method": "sequential_elo", "raw_elo": 1222.387305610914, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.59670002292491, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 32, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 131, "max_score": null, "measured_at": "2026-07-13T11:04:49Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1106.3424308016235, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.992113891672274, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 13, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 147, "max_score": null, "measured_at": "2026-07-13T10:56:42Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1061.0110888178588, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 7.242946177185584, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "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": "2026-07-13T10:41:12Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1979.7616482540543, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 147 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 2, "max_score": null, "measured_at": "2026-07-13T09:00:33Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1755.83086583758, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 60.316068241537906, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 103 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 69, "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": "2026-07-13T08:08:47Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1717.875826669142, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 53.58698477233553, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 93 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 107, "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": "2026-07-13T06:34:01Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1601.2168587128067, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 32.90441007321703, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 54 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 118, "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": "2026-07-13T06:14:51Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1574.074206871008, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.075303957431895, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 129, "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": "2026-07-13T05:46:51Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1555.1607564607773, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 24.739081750285404, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 2, "attempted_matches": 326, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 163, "draws": 290, "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": 24, "max_score": null, "measured_at": "2026-07-13T04:09:54Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 326, "rating_method": "sequential_elo", "raw_elo": 1503.0322461375365, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.497093457640895, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 2, "attempted_matches": 325, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 163, "draws": 287, "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": 20, "max_score": null, "measured_at": "2026-07-13T04:22:09Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 325, "rating_method": "sequential_elo", "raw_elo": 1501.245834006424, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.171975712097549, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 15, "max_score": null, "measured_at": "2026-07-13T03:35:09Z", "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": 164, "rating_method": "sequential_elo", "raw_elo": 1497.4232144200814, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.519546549031492, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 151, "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": "2026-07-13T03:20:15Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1490.2321929984787, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.244643810555974, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 147, "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": "2026-07-13T02:43:13Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1481.07722300102, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.587783971795917, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 3, "attempted_matches": 488, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 421, "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": 41, "max_score": null, "measured_at": "2026-07-13T10:41:12Z", "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": 488, "rating_method": "sequential_elo", "raw_elo": 1475.7825576526072, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.660343551755462, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 145, "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": "2026-07-13T03:20:57Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1471.674689049943, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.920800162399148, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 2, "attempted_matches": 326, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 163, "draws": 291, "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": 24, "max_score": null, "measured_at": "2026-07-13T03:46:25Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 326, "rating_method": "sequential_elo", "raw_elo": 1470.4467708737575, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.719984864483806, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 2, "attempted_matches": 326, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 163, "draws": 297, "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": 25, "max_score": null, "measured_at": "2026-07-13T10:28:30Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 326, "rating_method": "sequential_elo", "raw_elo": 1462.8521814784149, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 8.373533192314857, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 136, "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": 23, "max_score": null, "measured_at": "2026-07-13T03:35:49Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1461.958262259751, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 8.215126650850651, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 19, "max_score": null, "measured_at": "2026-07-13T03:45:11Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1459.9450873132312, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 7.858209030686404, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 31, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-03", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T08:09:45Z", "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": 24, "rating_method": "sequential_elo", "raw_elo": 1647.444720026088, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 56.25, "unilateral_faults": 1, "wins": 19 }, { "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": 31, "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": "2026-07-13T07:06:20Z", "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": 42, "rating_method": "sequential_elo", "raw_elo": 1591.4081011424776, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 87.5163455191311, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 1, "attempted_matches": 18, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 14, "draws": 6, "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": "2026-07-13T18:48:15Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 14, "rating_method": "sequential_elo", "raw_elo": 1506.600847615336, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.679296623862335, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 85.34944487358055, "unilateral_faults": 3, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 10, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 6, "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": 1, "max_score": null, "measured_at": "2026-07-13T16:11:38Z", "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": 6, "rating_method": "sequential_elo", "raw_elo": 1546.1471946417246, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 41.86144914266503, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 100.0, "unilateral_faults": 3, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 14, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 4, "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": 0, "max_score": null, "measured_at": "2026-07-13T18:14:57Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 4, "rating_method": "sequential_elo", "raw_elo": 1516.5700531655325, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 22.55529420366387, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 100.0, "unilateral_faults": 10, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 23, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 12, "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": 7, "max_score": null, "measured_at": "2026-07-13T14:18:39Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 12, "rating_method": "sequential_elo", "raw_elo": 1443.5649425457402, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.849828926322857, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 94.92504905630727, "unilateral_faults": 5, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 29, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 12, "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": 8, "max_score": null, "measured_at": "2026-07-08T19:50:24Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4", "model_slug": "gpt-5-4", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 14, "rating_method": "sequential_elo", "raw_elo": 1435.806116874855, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.816680906992, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 85.34944487358055, "unilateral_faults": 3, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 9, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 4, "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": 1, "max_score": null, "measured_at": "2026-07-10T13:21:23Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 4, "rating_method": "sequential_elo", "raw_elo": 1505.6825279027676, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.885461311644505, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 100.0, "unilateral_faults": 3, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 11, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 6, "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": 3, "max_score": null, "measured_at": "2026-07-11T21:30:40Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 6, "rating_method": "sequential_elo", "raw_elo": 1458.1502679833463, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 12.20052913984636, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 100.0, "unilateral_faults": 4, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 25, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 14, "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": "2026-07-13T02:19:36Z", "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": 20, "rating_method": "sequential_elo", "raw_elo": 1387.519862012822, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.931466072572777, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 65.3589451179962, "unilateral_faults": 1, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 8, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 2, "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": 0, "max_score": null, "measured_at": "2026-07-06T04:21:24Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 2, "rating_method": "sequential_elo", "raw_elo": 1501.7085052884202, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 0.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 100.0, "unilateral_faults": 6, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 18, "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": "2026-07-13T10:40:55Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1950.1957259270505, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 143 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 75, "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": "2026-07-13T08:02:34Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1682.9421776365198, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 53.980008192328675, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 76, "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": "2026-07-13T08:04:55Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1664.2766188843018, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.7494004136231, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 113, "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": "2026-07-13T06:42:32Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1564.3358756481528, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 33.556477501132086, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 92, "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": 16, "max_score": null, "measured_at": "2026-07-13T06:44:30Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Terra", "model_slug": "gpt-5-6-terra", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1559.5330174908072, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 32.71297130401039, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 54 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 79, "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": "2026-07-13T05:41:08Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1543.8369658067368, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 30.02664723694179, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 67 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 119, "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": "2026-07-13T05:32:22Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1525.5768328644149, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 26.86585216070314, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "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": 22, "max_score": null, "measured_at": "2026-07-13T05:17:57Z", "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": 162, "rating_method": "sequential_elo", "raw_elo": 1515.2953296100363, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.095418433766493, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 33, "max_score": null, "measured_at": "2026-07-13T05:27:45Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "DeepSeek V4 Pro", "model_slug": "deepseek-deepseek-v4-pro", "plugin_success_rate": null, "provider": "DeepSeek", "provider_key": "deepseek", "rank": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1514.6418355739393, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 24.99936261254212, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 144, "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": "2026-07-13T04:57:31Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1492.0699499263617, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 21.1288974607488, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "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": 27, "max_score": null, "measured_at": "2026-07-13T04:31:47Z", "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": 162, "rating_method": "sequential_elo", "raw_elo": 1491.2502398452857, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.95495017406873, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 124, "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": "2026-07-13T04:51:27Z", "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": 164, "rating_method": "sequential_elo", "raw_elo": 1485.9799093066515, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.08021683061268, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 139, "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": "2026-07-13T04:36:42Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1477.3556932736828, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.595161332852324, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 120, "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": "2026-07-13T05:12:08Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1463.3688992933912, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.17036811395091, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 29, "max_score": null, "measured_at": "2026-07-13T06:16:19Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1446.0160640705587, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.182279312501247, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 2, "attempted_matches": 324, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 162, "draws": 126, "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": 129, "max_score": null, "measured_at": "2026-07-13T07:13:17Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 324, "rating_method": "sequential_elo", "raw_elo": 1437.0778401194716, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.62667967015868, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 69 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 65, "max_score": null, "measured_at": "2026-07-13T06:10:54Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1436.212990375402, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.494229241597468, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugins": 2, "attempted_matches": 324, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 162, "draws": 212, "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": 67, "max_score": null, "measured_at": "2026-07-13T10:36:29Z", "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": 324, "rating_method": "sequential_elo", "raw_elo": 1434.5762059507615, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.195908274657215, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 127, "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": "2026-07-13T10:40:30Z", "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": 162, "rating_method": "sequential_elo", "raw_elo": 1419.3287857720795, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 8.570363520623602, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 105, "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": "2026-07-13T06:34:38Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1415.212118591015, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 7.861489901697698, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:18:49Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 2197.6393105415173, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 188 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 5, "max_score": null, "measured_at": "2026-07-13T11:15:47Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 2105.624209097691, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 92.87168842486112, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 187 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:17:33Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 2012.721991475772, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 85.67465290743922, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 176 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:14:22Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1969.2325757485887, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 82.30557434685794, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 169 }, { "admitted_plugins": 2, "attempted_matches": 384, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 192, "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": "2026-07-13T11:16:50Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 384, "rating_method": "sequential_elo", "raw_elo": 1952.804406401529, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 81.03290162382152, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 319 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:17:54Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Sol", "model_slug": "gpt-5-6-sol", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1938.6627504861824, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 79.9373626528132, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 168 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:15:35Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1935.910063859551, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 79.72411496155975, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 168 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:18:09Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.5", "model_slug": "gpt-5-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1895.835343435012, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 76.61956919689428, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 163 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 57, "max_score": null, "measured_at": "2026-07-13T10:52:12Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1731.406709512891, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 63.88145864678119, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 135 }, { "admitted_plugins": 1, "attempted_matches": 193, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": 64, "max_score": null, "measured_at": "2026-07-13T10:52:13Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 193, "rating_method": "sequential_elo", "raw_elo": 1727.7505173272575, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 63.60397357250988, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 129 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 64, "max_score": null, "measured_at": "2026-07-13T10:37:08Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "O3", "model_slug": "o3", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1684.1981360032778, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 60.22426090734482, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 128 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 80, "max_score": null, "measured_at": "2026-07-13T10:06:04Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1650.3489022497863, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 57.601996942098886, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 112 }, { "admitted_plugins": 2, "attempted_matches": 384, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 192, "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": 137, "max_score": null, "measured_at": "2026-07-13T10:58:23Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4 Mini", "model_slug": "gpt-5-4-mini", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 384, "rating_method": "sequential_elo", "raw_elo": 1643.207774355121, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 57.04878139560334, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 247 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 64, "max_score": null, "measured_at": "2026-07-13T09:53:57Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1643.0317640516944, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 57.03514606549368, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 128 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T09:47:56Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1607.776140994234, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 54.30393062383434, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 115 }, { "admitted_plugins": 3, "attempted_matches": 585, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 293, "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": 233, "max_score": null, "measured_at": "2026-07-13T11:14:44Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GLM-5.2", "model_slug": "z-ai-glm-5-2", "plugin_success_rate": null, "provider": "Zhipu", "provider_key": "z-ai", "rank": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 581, "rating_method": "sequential_elo", "raw_elo": 1578.1127087882876, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 52.01544202340519, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 348 }, { "admitted_plugins": 1, "attempted_matches": 193, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": 79, "max_score": null, "measured_at": "2026-07-13T09:20:12Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 193, "rating_method": "sequential_elo", "raw_elo": 1576.6779912306322, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 51.90054642237549, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 114 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 102, "max_score": null, "measured_at": "2026-07-13T09:14:16Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1552.562062108092, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.02655493811615, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 90 }, { "admitted_plugins": 2, "attempted_matches": 392, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 196, "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": 237, "max_score": null, "measured_at": "2026-07-13T11:03:25Z", "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": 388, "rating_method": "sequential_elo", "raw_elo": 1416.4311333710273, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.49201794250497, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 151 }, { "admitted_plugins": 2, "attempted_matches": 384, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 192, "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": 231, "max_score": null, "measured_at": "2026-07-13T10:59:39Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 384, "rating_method": "sequential_elo", "raw_elo": 1374.2089887589111, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 36.20973294620973, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 153 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 147, "max_score": null, "measured_at": "2026-07-13T10:00:53Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1215.9047396936294, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.94607194601389, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 164, "max_score": null, "measured_at": "2026-07-13T10:58:15Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 988.8038436102726, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 6.352808222192618, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 6, "max_score": null, "measured_at": "2026-07-13T11:18:53Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 177, "rating_method": "sequential_elo", "raw_elo": 2111.368816314729, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 99.85042729198668, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 162 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 16, "max_score": null, "measured_at": "2026-07-13T11:23:24Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 2053.838860363551, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 95.07321615577396, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 154 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 13, "max_score": null, "measured_at": "2026-07-13T11:18:24Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 2026.2525667066411, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 92.7858495768554, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 153 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 16, "max_score": null, "measured_at": "2026-07-13T11:17:43Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 2012.9222938793916, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 91.68054630806056, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 153 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 15, "max_score": null, "measured_at": "2026-07-13T11:15:14Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1998.960307994121, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 90.52286342805895, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 159 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 14, "max_score": null, "measured_at": "2026-07-13T11:17:23Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1975.7342160431551, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 88.59703072475118, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 155 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 21, "max_score": null, "measured_at": "2026-07-13T11:14:59Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1958.6857036677432, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 87.18342301387884, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 151 }, { "admitted_plugins": 1, "attempted_matches": 184, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 92, "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": 19, "max_score": null, "measured_at": "2026-07-13T11:18:54Z", "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": 180, "rating_method": "sequential_elo", "raw_elo": 1949.4731722166168, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 86.44725003634304, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 154 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 19, "max_score": null, "measured_at": "2026-07-13T11:17:13Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1946.3805267610455, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 86.16311739565705, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 143 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 42, "max_score": null, "measured_at": "2026-07-13T11:17:15Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1834.204736399648, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 76.86186232211922, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 129 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 35, "max_score": null, "measured_at": "2026-07-13T11:17:14Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1800.8372467972556, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 74.09513760410667, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 140 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 37, "max_score": null, "measured_at": "2026-07-13T11:01:21Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT 5", "model_slug": "gpt-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1771.0027793472395, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 71.6213596985377, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 131 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 15, "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": 61, "max_score": null, "measured_at": "2026-07-13T10:53:03Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1640.6007590549266, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 60.808844369375834, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 100 }, { "admitted_plugins": 2, "attempted_matches": 352, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 176, "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": 136, "max_score": null, "measured_at": "2026-07-13T11:17:35Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4 Mini", "model_slug": "gpt-5-4-mini", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 352, "rating_method": "sequential_elo", "raw_elo": 1620.0782625848524, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 59.10718509156764, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 202 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 73, "max_score": null, "measured_at": "2026-07-13T10:09:54Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 177, "rating_method": "sequential_elo", "raw_elo": 1543.393215932306, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 52.75572069190129, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 94 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 78, "max_score": null, "measured_at": "2026-07-13T09:04:51Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 177, "rating_method": "sequential_elo", "raw_elo": 1501.6128850793782, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 49.29143028603119, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 88 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 88, "max_score": null, "measured_at": "2026-07-13T10:36:21Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1386.8086718651762, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.765222291989005, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 77 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 110, "max_score": null, "measured_at": "2026-07-13T10:53:27Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1327.686745679047, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.863022680785726, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 62 }, { "admitted_plugins": 1, "attempted_matches": 184, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 92, "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": 105, "max_score": null, "measured_at": "2026-07-13T11:23:24Z", "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": 180, "rating_method": "sequential_elo", "raw_elo": 1327.3034955719472, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.85894526176792, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 68 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 108, "max_score": null, "measured_at": "2026-07-13T11:02:44Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1326.1159042236277, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.73277356901328, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 65 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 130, "max_score": null, "measured_at": "2026-07-13T10:57:22Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1253.9530728509649, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.749264121356106, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 143, "max_score": null, "measured_at": "2026-07-13T11:14:06Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1185.296173265826, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.05645524038202, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 145, "max_score": null, "measured_at": "2026-07-13T11:14:58Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1155.9492312898828, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.623101376173416, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 2, "attempted_matches": 352, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 176, "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": 286, "max_score": null, "measured_at": "2026-07-13T11:15:39Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 352, "rating_method": "sequential_elo", "raw_elo": 1141.355106683629, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.41300359036388, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 65 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 3, "max_score": null, "measured_at": "2026-07-13T11:18:50Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 2162.280337984363, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 179 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 5, "max_score": null, "measured_at": "2026-07-13T11:18:50Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 2158.352458516296, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 99.70622072012152, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 177 }, { "admitted_plugins": 1, "attempted_matches": 183, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T11:18:43Z", "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": 183, "rating_method": "sequential_elo", "raw_elo": 1969.49620679625, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 85.5870460569821, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 159 }, { "admitted_plugins": 2, "attempted_matches": 364, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 182, "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": "2026-07-13T11:18:55Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 364, "rating_method": "sequential_elo", "raw_elo": 1942.8740956603929, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 83.58987122827983, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 317 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T11:17:34Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1931.310445460898, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 82.72498704433467, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 155 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T11:15:24Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Sol", "model_slug": "gpt-5-6-sol", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1877.1088979226424, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 78.67107150707326, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 148 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 29, "max_score": null, "measured_at": "2026-07-13T11:14:02Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 1841.381570761984, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 75.99890487605245, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 153 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T11:17:05Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1837.7205673472693, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 75.72508615133052, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 148 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T11:13:02Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1752.2710306808017, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 69.33402869859839, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 131 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 54, "max_score": null, "measured_at": "2026-07-13T11:15:13Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Gemini 3.5 Flash", "model_slug": "google-gemini-3-5-flash", "plugin_success_rate": null, "provider": "Google", "provider_key": "google", "rank": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1732.245154505618, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 67.83622625086294, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 128 }, { "admitted_plugins": 3, "attempted_matches": 555, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 278, "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": 184, "max_score": null, "measured_at": "2026-07-13T11:17:36Z", "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": 549, "rating_method": "sequential_elo", "raw_elo": 1693.5342145811692, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 64.94690677132208, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 365 }, { "admitted_plugins": 2, "attempted_matches": 365, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 183, "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": 127, "max_score": null, "measured_at": "2026-07-13T11:14:44Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 365, "rating_method": "sequential_elo", "raw_elo": 1668.7527870423269, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 63.090428051106514, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 238 }, { "admitted_plugins": 1, "attempted_matches": 183, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T10:58:57Z", "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": 183, "rating_method": "sequential_elo", "raw_elo": 1668.6316311462508, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 63.084375317216946, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 119 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 65, "max_score": null, "measured_at": "2026-07-13T10:59:43Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 1668.553096042562, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 63.07248356950672, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 117 }, { "admitted_plugins": 2, "attempted_matches": 364, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 182, "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": 168, "max_score": null, "measured_at": "2026-07-13T11:13:06Z", "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": 364, "rating_method": "sequential_elo", "raw_elo": 1581.3569640673554, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 56.55079239539596, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 196 }, { "admitted_plugins": 1, "attempted_matches": 183, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T10:36:53Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Sonnet 5", "model_slug": "claude-sonnet-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 183, "rating_method": "sequential_elo", "raw_elo": 1534.2555897441107, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 53.03394047139757, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 99 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 85, "max_score": null, "measured_at": "2026-07-13T10:40:14Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 1530.122360655427, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 52.71878456074053, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 97 }, { "admitted_plugins": 1, "attempted_matches": 172, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-12T07:19:59Z", "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": 168, "rating_method": "sequential_elo", "raw_elo": 1516.4605568504155, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 51.60719199001697, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 4, "wins": 80 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 118, "max_score": null, "measured_at": "2026-07-13T10:08:01Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1379.0615665243683, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 41.42044109616099, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 64 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 111, "max_score": null, "measured_at": "2026-07-13T10:08:31Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-OSS 120B", "model_slug": "openai-gpt-oss-120b", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1374.6495646773667, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 41.09045267977192, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 71 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 122, "max_score": null, "measured_at": "2026-07-13T10:52:56Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 1273.086757806722, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 33.49422970310896, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 60 }, { "admitted_plugins": 1, "attempted_matches": 183, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 154, "max_score": null, "measured_at": "2026-07-13T11:15:27Z", "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": 183, "rating_method": "sequential_elo", "raw_elo": 1073.1062106896916, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.54303167533976, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "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": "2026-07-13T11:18:07Z", "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": 189, "rating_method": "sequential_elo", "raw_elo": 2132.1542218237096, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 98.16260901359112, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 184 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-08", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T11:13:02Z", "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": 189, "rating_method": "sequential_elo", "raw_elo": 2028.7089535272355, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 87.01781118744486, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 176 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 8, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 8, "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": "2026-07-13T11:06:38Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1919.2682873054955, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 75.22709210395418, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 162 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-08", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T11:01:31Z", "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": 189, "rating_method": "sequential_elo", "raw_elo": 1882.6097202931392, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 71.27763820744504, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 162 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 9, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "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": 29, "max_score": null, "measured_at": "2026-07-13T10:32:11Z", "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": 188, "rating_method": "sequential_elo", "raw_elo": 1802.4501299122312, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 62.633290327266224, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 150 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 64, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 64, "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": "2026-07-13T10:41:27Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.5", "model_slug": "gpt-5-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1747.3200463010708, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 56.70204582476052, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 113 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 35, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 35, "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": "2026-07-13T09:23:48Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1686.9911699498823, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.194183278796665, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 114 }, { "admitted_plugins": 3, "attempted_matches": 562, "capped_draws": 258, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 282, "draws": 258, "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": 99, "max_score": null, "measured_at": "2026-07-13T11:18:54Z", "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": 562, "rating_method": "sequential_elo", "raw_elo": 1646.9348350260022, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 45.87307214409487, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 205 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 32, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "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": 36, "max_score": null, "measured_at": "2026-07-13T09:24:44Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1625.9873576107975, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 43.621865701208215, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 120 }, { "admitted_plugins": 2, "attempted_matches": 377, "capped_draws": 140, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 190, "draws": 140, "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": 82, "max_score": null, "measured_at": "2026-07-13T11:06:04Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 377, "rating_method": "sequential_elo", "raw_elo": 1576.8230098237732, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 38.32915139307305, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 155 }, { "admitted_plugins": 3, "attempted_matches": 567, "capped_draws": 195, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 284, "draws": 195, "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": 194, "max_score": null, "measured_at": "2026-07-13T11:17:36Z", "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": 564, "rating_method": "sequential_elo", "raw_elo": 1525.4849294334806, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 32.79405211184169, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 175 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 114, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 114, "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": "2026-07-13T11:05:58Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1447.9378811498193, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 24.422777320201146, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 1, "attempted_matches": 190, "capped_draws": 58, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 73, "max_score": null, "measured_at": "2026-07-13T10:26:59Z", "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": 190, "rating_method": "sequential_elo", "raw_elo": 1441.216892792548, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.731857066176303, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 59 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 136, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 136, "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": 43, "max_score": null, "measured_at": "2026-07-13T11:07:38Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1407.0770575585177, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.020588361400733, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 1, "attempted_matches": 187, "capped_draws": 109, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "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": 55, "max_score": null, "measured_at": "2026-07-13T11:02:32Z", "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": 186, "rating_method": "sequential_elo", "raw_elo": 1402.0270488022595, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.476519719735425, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 2, "attempted_matches": 381, "capped_draws": 256, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 192, "draws": 256, "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": 99, "max_score": null, "measured_at": "2026-07-13T11:16:33Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 378, "rating_method": "sequential_elo", "raw_elo": 1383.6671916058622, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 17.523477184350448, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 127, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 127, "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": 53, "max_score": null, "measured_at": "2026-07-13T11:17:51Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Gemini 3.1 Flash Lite", "model_slug": "google-gemini-3-1-flash-lite", "plugin_success_rate": null, "provider": "Google", "provider_key": "google", "rank": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1376.104841957335, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.683760232020177, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 187, "capped_draws": 131, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "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": 46, "max_score": null, "measured_at": "2026-07-13T11:13:38Z", "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": 187, "rating_method": "sequential_elo", "raw_elo": 1375.233252453259, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.598251014653428, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 129, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 129, "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": 49, "max_score": null, "measured_at": "2026-07-13T11:17:20Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1370.494322139764, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.079304270948928, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 127, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 127, "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": "2026-07-13T11:13:11Z", "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": 186, "rating_method": "sequential_elo", "raw_elo": 1360.7459680636564, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.029053862157538, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 133, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 133, "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": 52, "max_score": null, "measured_at": "2026-07-13T11:15:45Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1355.3864631081572, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.451641282917274, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 105, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 105, "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": 81, "max_score": null, "measured_at": "2026-07-13T11:17:43Z", "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": 186, "rating_method": "sequential_elo", "raw_elo": 1272.3937366442383, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 5.510322141763682, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 25, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "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": 123, "max_score": null, "measured_at": "2026-07-13T11:15:51Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1256.275063394386, "reasoning_level": "XHigh", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "highest", "source": "public_redacted_snapshot", "track_id": "full_freedom/highest" }, "provider_route": "unknown_legacy", "reasoning_bucket": "highest", "reasoning_bucket_label": "Highest reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "highest" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 3.7904762066821025, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/highest", "track_name": "XHigh variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 7, "attempted_matches": 1245, "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-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 4.0372 }, "codegen_evaluated_cells": 8, "conditional_success_score": 72.21883276340077, "contributing_entrants": null, "distinct_rated_opponents": 621, "draws": 170, "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": "2026-07-13T11:16:50Z", "losses": 128, "max_score": 86.59651961160996, "measured_at": null, "min_score": 42.101358265742746, "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1239, "rating_method": "sequential_elo", "raw_elo": 1859.9976797834684, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 69.84775922173306, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 0, "wins": 941 }, { "admitted_plugins": 8, "attempted_matches": 1248, "capped_draws": 18, "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-2026-07-12": 10 }, "run_count": 9, "token_priced_attempt_count": 10, "total": 4.1199200000000005 }, "codegen_evaluated_cells": 9, "conditional_success_score": 55.49385388463494, "contributing_entrants": null, "distinct_rated_opponents": 623, "draws": 244, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T18:48:15Z", "losses": 172, "max_score": 80.83653200086476, "measured_at": null, "min_score": 25.03713437216872, "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1242, "rating_method": "sequential_elo", "raw_elo": 1763.3361589483193, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.1111111111111111, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 53.8836188826375, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 3, "wins": 826 }, { "admitted_plugins": 8, "attempted_matches": 1264, "capped_draws": 126, "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": 50.26404387209092, "contributing_entrants": null, "distinct_rated_opponents": 625, "draws": 374, "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": "2026-07-13T19:18:02Z", "losses": 265, "max_score": 92.37554944921584, "measured_at": null, "min_score": 15.52961769268853, "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1243, "rating_method": "sequential_elo", "raw_elo": 1666.234014034844, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 8, "repaired_rate": 1.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 50.26404387209092, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 11, "wins": 604 }, { "admitted_plugins": 8, "attempted_matches": 1165, "capped_draws": 64, "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-2026-07-12": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 3.98915 }, "codegen_evaluated_cells": 8, "conditional_success_score": 49.07193775824096, "contributing_entrants": null, "distinct_rated_opponents": 600, "draws": 343, "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": "2026-07-13T11:18:45Z", "losses": 234, "max_score": 100.0, "measured_at": null, "min_score": 14.518901175227816, "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1156, "rating_method": "sequential_elo", "raw_elo": 1650.4493101930552, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 49.07193775824096, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 9, "wins": 579 }, { "admitted_plugins": 8, "attempted_matches": 1266, "capped_draws": 212, "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-2026-07-12": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 3.542855 }, "codegen_evaluated_cells": 8, "conditional_success_score": 47.20981092662286, "contributing_entrants": null, "distinct_rated_opponents": 639, "draws": 444, "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": "2026-07-13T18:28:37Z", "losses": 254, "max_score": 85.91160100452133, "measured_at": null, "min_score": 19.541203899412803, "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1257, "rating_method": "sequential_elo", "raw_elo": 1592.8853853515752, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 47.20981092662286, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 6, "wins": 559 }, { "admitted_plugins": 6, "attempted_matches": 1080, "capped_draws": 135, "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-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 0.390976 }, "codegen_evaluated_cells": 8, "conditional_success_score": 45.90073295157999, "contributing_entrants": null, "distinct_rated_opponents": 541, "draws": 275, "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": "2026-07-13T11:17:56Z", "losses": 344, "max_score": 71.26903378287814, "measured_at": null, "min_score": 21.69121170153766, "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1078, "rating_method": "sequential_elo", "raw_elo": 1573.8300265086018, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 42.715445121088194, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 1, "wins": 459 }, { "admitted_plugins": 8, "attempted_matches": 1256, "capped_draws": 161, "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-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 1.743525 }, "codegen_evaluated_cells": 8, "conditional_success_score": 41.46092745060459, "contributing_entrants": null, "distinct_rated_opponents": 626, "draws": 448, "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": "2026-07-13T15:25:01Z", "losses": 284, "max_score": 91.70584983423836, "measured_at": null, "min_score": 8.792181774741303, "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1246, "rating_method": "sequential_elo", "raw_elo": 1596.5152268113136, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 41.46092745060459, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 5, "wins": 514 }, { "admitted_plugins": 6, "attempted_matches": 898, "capped_draws": 128, "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": 43.54352147792685, "contributing_entrants": null, "distinct_rated_opponents": 449, "draws": 244, "entry_count": 6, "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": "2026-07-13T11:18:03Z", "losses": 380, "max_score": 70.89086607159972, "measured_at": null, "min_score": 13.264083848544765, "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 898, "rating_method": "sequential_elo", "raw_elo": 1538.154704225489, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 40.521812669775365, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 0, "wins": 449 }, { "admitted_plugins": 7, "attempted_matches": 1125, "capped_draws": 142, "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-2026-07-12": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 1.42050125 }, "codegen_evaluated_cells": 8, "conditional_success_score": 41.53044627492922, "contributing_entrants": null, "distinct_rated_opponents": 571, "draws": 270, "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": "2026-07-13T11:18:07Z", "losses": 422, "max_score": 68.10303654582466, "measured_at": null, "min_score": 15.984096147083603, "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1122, "rating_method": "sequential_elo", "raw_elo": 1503.3040011074631, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 40.16692738978267, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 0, "wins": 430 }, { "admitted_plugins": 6, "attempted_matches": 1076, "capped_draws": 176, "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": 42.54064538804611, "contributing_entrants": null, "distinct_rated_opponents": 538, "draws": 338, "entry_count": 6, "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": "2026-07-13T11:16:59Z", "losses": 328, "max_score": 81.88087560362533, "measured_at": null, "min_score": 13.009111045617562, "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1076, "rating_method": "sequential_elo", "raw_elo": 1547.107092405945, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 39.58853130745503, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 0, "wins": 410 }, { "admitted_plugins": 6, "attempted_matches": 1067, "capped_draws": 24, "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": 42.10767006502641, "contributing_entrants": null, "distinct_rated_opponents": 534, "draws": 281, "entry_count": 6, "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": "2026-07-13T10:53:23Z", "losses": 315, "max_score": 59.58264825078116, "measured_at": null, "min_score": 12.540709613495318, "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1066, "rating_method": "sequential_elo", "raw_elo": 1585.212525423465, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 39.1856023679816, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 0, "wins": 470 }, { "admitted_plugins": 8, "attempted_matches": 1271, "capped_draws": 156, "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-2026-07-12": 11 }, "run_count": 8, "token_priced_attempt_count": 11, "total": 1.33952 }, "codegen_evaluated_cells": 8, "conditional_success_score": 37.8447761314094, "contributing_entrants": null, "distinct_rated_opponents": 636, "draws": 459, "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": "2026-07-13T15:06:27Z", "losses": 344, "max_score": 66.27290316140129, "measured_at": null, "min_score": 10.94878978246065, "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1259, "rating_method": "sequential_elo", "raw_elo": 1518.270434233332, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 37.8447761314094, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 3, "wins": 456 }, { "admitted_plugins": 8, "attempted_matches": 1168, "capped_draws": 169, "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": 0.309345, "mean": 0.239705, "median": 0.232815, "min": 0.175235, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 1.91764 }, "codegen_evaluated_cells": 8, "conditional_success_score": 37.21615883516933, "contributing_entrants": null, "distinct_rated_opponents": 588, "draws": 377, "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": "2026-07-13T17:37:51Z", "losses": 342, "max_score": 59.526947576565824, "measured_at": null, "min_score": 14.877885447048715, "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1143, "rating_method": "sequential_elo", "raw_elo": 1526.0021889372076, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 37.21615883516933, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 16, "wins": 424 }, { "admitted_plugins": 16, "attempted_matches": 2233, "capped_draws": 373, "codegen_cost_usd": { "admitted_cell_count": 16, "cell_count": 8, "cost_basis_counts": { "provider_reported": 52 }, "evidence_basis": "Provider-reported", "failed_cell_count": 8, "max": 0.1697954668, "mean": 0.12351497933333334, "median": 0.12954777533333334, "min": 0.05546312440000001, "recorded_attempt_count": 52, "run_count": 24, "total": 2.964359504 }, "codegen_evaluated_cells": 24, "conditional_success_score": 40.54469529572177, "contributing_entrants": null, "distinct_rated_opponents": 1135, "draws": 690, "entry_count": 16, "failed_game_aliases": [ "GB2-01", "GB2-02", "GB2-03", "GB2-04", "GB2-05", "GB2-06" ], "first_pass_admitted": 3, "first_pass_rate": 0.125, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T19:18:02Z", "losses": 574, "max_score": 63.63124555669186, "measured_at": null, "min_score": 17.458145034751666, "model_code_failure_rate": 0.3333333333333333, "model_code_failures": 8, "model_display_name": "GLM-5.2", "model_slug": "z-ai-glm-5-2", "plugin_success_rate": 0.6666666666666666, "provider": "Zhipu", "provider_key": "z-ai", "rank": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 2192, "rating_method": "sequential_elo", "raw_elo": 1565.7790885008485, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 13, "repaired_rate": 0.5416666666666666, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 36.63626790496484, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 19, "wins": 928 }, { "admitted_plugins": 7, "attempted_matches": 1243, "capped_draws": 166, "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-2026-07-12": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 0.624428 }, "codegen_evaluated_cells": 8, "conditional_success_score": 37.78697868650787, "contributing_entrants": null, "distinct_rated_opponents": 622, "draws": 432, "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": "2026-07-13T11:15:41Z", "losses": 374, "max_score": 64.72154766303917, "measured_at": null, "min_score": 9.95306063713581, "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1240, "rating_method": "sequential_elo", "raw_elo": 1523.8821688444857, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 36.54636454259518, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 0, "wins": 434 }, { "admitted_plugins": 7, "attempted_matches": 1240, "capped_draws": 172, "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": 37.34802155864339, "contributing_entrants": null, "distinct_rated_opponents": 620, "draws": 427, "entry_count": 7, "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": "2026-07-13T11:17:21Z", "losses": 383, "max_score": 79.21328749427038, "measured_at": null, "min_score": 14.026596031966744, "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1239, "rating_method": "sequential_elo", "raw_elo": 1519.8417904150533, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 36.121819162913, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 0, "wins": 429 }, { "admitted_plugins": 25, "attempted_matches": 3793, "capped_draws": 340, "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": 0.0362005625, "mean": 0.024352715625, "median": 0.025206018750000003, "min": 0.016582062499999998, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 49 }, "run_count": 32, "token_priced_attempt_count": 49, "total": 0.7792869 }, "codegen_evaluated_cells": 32, "conditional_success_score": 35.72995441277762, "contributing_entrants": null, "distinct_rated_opponents": 1913, "draws": 1000, "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": "2026-07-13T15:06:27Z", "losses": 1692, "max_score": 52.691719485250296, "measured_at": null, "min_score": 15.263222308732672, "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 3776, "rating_method": "sequential_elo", "raw_elo": 1437.9304796707424, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 12, "repaired_rate": 0.375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 33.59154427013184, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 17, "wins": 1084 }, { "admitted_plugins": 23, "attempted_matches": 2941, "capped_draws": 392, "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": 0.29749325, "mean": 0.24155631250000004, "median": 0.24021375, "min": 0.17873725, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 26 }, "run_count": 24, "token_priced_attempt_count": 26, "total": 5.7973514999999995 }, "codegen_evaluated_cells": 24, "conditional_success_score": 33.04225957146811, "contributing_entrants": null, "distinct_rated_opponents": 1494, "draws": 1194, "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": "2026-07-13T18:48:15Z", "losses": 874, "max_score": 45.74532923505766, "measured_at": null, "min_score": 14.464677503373531, "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 2898, "rating_method": "sequential_elo", "raw_elo": 1487.1880530521207, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 1, "repaired_rate": 0.041666666666666664, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 32.69255681562888, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 34, "wins": 830 }, { "admitted_plugins": 8, "attempted_matches": 1275, "capped_draws": 164, "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": 0.4852846 }, "codegen_evaluated_cells": 8, "conditional_success_score": 31.658220453712367, "contributing_entrants": null, "distinct_rated_opponents": 641, "draws": 452, "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": "2026-07-13T18:28:37Z", "losses": 493, "max_score": 61.07709054345052, "measured_at": null, "min_score": 11.56683145120459, "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1263, "rating_method": "sequential_elo", "raw_elo": 1426.6853726769298, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 8, "repaired_rate": 1.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 31.658220453712367, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 3, "wins": 318 }, { "admitted_plugins": 8, "attempted_matches": 1249, "capped_draws": 141, "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-2026-07-12": 9 }, "run_count": 9, "token_priced_attempt_count": 9, "total": 0.31504800000000005 }, "codegen_evaluated_cells": 9, "conditional_success_score": 31.113379340231347, "contributing_entrants": null, "distinct_rated_opponents": 623, "draws": 428, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T18:48:15Z", "losses": 335, "max_score": 70.48739385233826, "measured_at": null, "min_score": 6.647988945759312, "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1242, "rating_method": "sequential_elo", "raw_elo": 1553.2697047814945, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 30.210579319381903, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 4, "wins": 479 }, { "admitted_plugins": 4, "attempted_matches": 714, "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": 32.6009150084153, "contributing_entrants": null, "distinct_rated_opponents": 357, "draws": 135, "entry_count": 4, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:13:11Z", "losses": 352, "max_score": 54.462035234390775, "measured_at": null, "min_score": 19.649994804578235, "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 714, "rating_method": "sequential_elo", "raw_elo": 1376.3819328292898, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 4, "repaired_rate": 0.5714285714285714, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 28.34459639732571, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 0, "wins": 227 }, { "admitted_plugins": 6, "attempted_matches": 940, "capped_draws": 133, "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": 29.554104055142627, "contributing_entrants": null, "distinct_rated_opponents": 468, "draws": 261, "entry_count": 6, "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": "2026-07-13T18:48:15Z", "losses": 435, "max_score": 46.68447767783332, "measured_at": null, "min_score": 13.87184383892639, "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 921, "rating_method": "sequential_elo", "raw_elo": 1387.397968636173, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 27.503192840124793, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 4, "wins": 225 }, { "admitted_plugins": 5, "attempted_matches": 887, "capped_draws": 171, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 21 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.065385, "mean": 0.03551179375, "median": 0.032728425, "min": 0.0200767, "recorded_attempt_count": 21, "run_count": 9, "total": 0.3177278 }, "codegen_evaluated_cells": 9, "conditional_success_score": 31.17253490312569, "contributing_entrants": null, "distinct_rated_opponents": 445, "draws": 329, "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": "2026-07-13T11:15:55Z", "losses": 343, "max_score": 65.22833892015394, "measured_at": null, "min_score": 10.23547336764388, "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 887, "rating_method": "sequential_elo", "raw_elo": 1425.5035909594158, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 5, "repaired_rate": 0.5555555555555556, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 26.91249694943565, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 0, "wins": 215 }, { "admitted_plugins": 15, "attempted_matches": 2627, "capped_draws": 229, "codegen_cost_usd": { "admitted_cell_count": 15, "cell_count": 8, "cost_basis_counts": { "provider_reported": 48 }, "evidence_basis": "Provider-reported", "failed_cell_count": 6, "max": 0.03389426, "mean": 0.0208777869875, "median": 0.0210709803, "min": 0.0085050301, "recorded_attempt_count": 48, "run_count": 21, "total": 0.43794584700000005 }, "codegen_evaluated_cells": 21, "conditional_success_score": 26.681060316732005, "contributing_entrants": null, "distinct_rated_opponents": 1317, "draws": 1016, "entry_count": 15, "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" ], "infra_failures_excluded": 1, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:14:05Z", "losses": 1100, "max_score": 41.76631544139825, "measured_at": null, "min_score": 13.67840064525899, "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 2627, "rating_method": "sequential_elo", "raw_elo": 1354.0385580783118, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 14, "repaired_rate": 0.6666666666666666, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 24.52850481545789, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 0, "wins": 511 }, { "admitted_plugins": 5, "attempted_matches": 612, "capped_draws": 6, "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": 0.81977125 }, "codegen_evaluated_cells": 8, "conditional_success_score": 23.95203502083948, "contributing_entrants": null, "distinct_rated_opponents": 329, "draws": 22, "entry_count": 5, "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": "2026-07-13T19:18:02Z", "losses": 445, "max_score": 41.07604676062133, "measured_at": null, "min_score": 1.9931136856735752, "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 604, "rating_method": "sequential_elo", "raw_elo": 1278.3737896571654, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 5, "repaired_rate": 0.625, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 21.296705353045024, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 4, "wins": 137 }, { "admitted_plugins": 14, "attempted_matches": 2016, "capped_draws": 291, "codegen_cost_usd": { "admitted_cell_count": 14, "cell_count": 8, "cost_basis_counts": { "provider_reported": 24 }, "evidence_basis": "Provider-reported", "failed_cell_count": 2, "max": 0.004911942999999999, "mean": 0.00318583316625, "median": 0.002947833025, "min": 0.001831717, "recorded_attempt_count": 24, "run_count": 16, "total": 0.05097333066 }, "codegen_evaluated_cells": 16, "conditional_success_score": 21.703418450856987, "contributing_entrants": null, "distinct_rated_opponents": 1023, "draws": 709, "entry_count": 14, "failed_game_aliases": [ "GB2-03", "GB2-04" ], "first_pass_admitted": 10, "first_pass_rate": 0.625, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:18:50Z", "losses": 1008, "max_score": 40.58862492867081, "measured_at": null, "min_score": 6.7491967108184525, "model_code_failure_rate": 0.125, "model_code_failures": 2, "model_display_name": "DeepSeek V4 Flash", "model_slug": "deepseek-deepseek-v4-flash", "plugin_success_rate": 0.875, "provider": "DeepSeek", "provider_key": "deepseek", "rank": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 2001, "rating_method": "sequential_elo", "raw_elo": 1364.690832601796, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 4, "repaired_rate": 0.25, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 20.990856376900997, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 9, "wins": 284 }, { "admitted_plugins": 7, "attempted_matches": 1238, "capped_draws": 142, "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": 20.378413987999977, "contributing_entrants": null, "distinct_rated_opponents": 620, "draws": 402, "entry_count": 7, "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": "2026-07-13T11:16:26Z", "losses": 619, "max_score": 55.56333293433932, "measured_at": null, "min_score": 5.4413534752207235, "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1238, "rating_method": "sequential_elo", "raw_elo": 1320.4337867379556, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 7, "repaired_rate": 0.875, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 19.70935418214024, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 0, "wins": 217 }, { "admitted_plugins": 6, "attempted_matches": 1080, "capped_draws": 160, "codegen_cost_usd": { "admitted_cell_count": 6, "cell_count": 8, "cost_basis_counts": { "provider_reported": 18 }, "evidence_basis": "Provider-reported", "failed_cell_count": 2, "max": 0.0149315, "mean": 0.0101355, "median": 0.010566625, "min": 0.00402875, "recorded_attempt_count": 18, "run_count": 8, "total": 0.081084 }, "codegen_evaluated_cells": 8, "conditional_success_score": 20.76901219190074, "contributing_entrants": null, "distinct_rated_opponents": 541, "draws": 282, "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": "2026-07-13T11:17:36Z", "losses": 611, "max_score": 35.400601409407294, "measured_at": null, "min_score": 9.023826409826338, "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1079, "rating_method": "sequential_elo", "raw_elo": 1264.5650113951283, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 4, "repaired_rate": 0.5, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 19.327743664533575, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 0, "wins": 186 }, { "admitted_plugins": 7, "attempted_matches": 1075, "capped_draws": 164, "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": 19.90626075152395, "contributing_entrants": null, "distinct_rated_opponents": 532, "draws": 449, "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": "2026-07-13T18:14:57Z", "losses": 433, "max_score": 34.62666056621864, "measured_at": null, "min_score": 0.034968617309127016, "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1061, "rating_method": "sequential_elo", "raw_elo": 1382.444226284319, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 6, "repaired_rate": 0.75, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 19.25270258150882, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 9, "wins": 179 }, { "admitted_plugins": 4, "attempted_matches": 696, "capped_draws": 0, "codegen_cost_usd": { "admitted_cell_count": 4, "cell_count": 8, "cost_basis_counts": { "provider_reported": 19 }, "evidence_basis": "Provider-reported", "failed_cell_count": 4, "max": 0.0711619, "mean": 0.0393452125, "median": 0.033877925, "min": 0.02387735, "recorded_attempt_count": 19, "run_count": 8, "total": 0.3147617 }, "codegen_evaluated_cells": 8, "conditional_success_score": 26.55370140303076, "contributing_entrants": null, "distinct_rated_opponents": 348, "draws": 283, "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": "2026-07-13T10:57:42Z", "losses": 258, "max_score": 43.17328153297657, "measured_at": null, "min_score": 9.873513428324548, "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": 696, "rating_method": "sequential_elo", "raw_elo": 1421.3860732227265, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": 4, "repaired_rate": 0.5, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 22.328912321526097, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": null, "unilateral_faults": 0, "wins": 155 }, { "admitted_plugins": 1, "attempted_matches": 180, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 87, "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": 11, "max_score": null, "measured_at": "2026-07-13T11:18:43Z", "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": 174, "rating_method": "sequential_elo", "raw_elo": 2063.2330904400105, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 90.1184118419254, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 163 }, { "admitted_plugins": 1, "attempted_matches": 180, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 87, "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": "2026-07-13T11:15:57Z", "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": 174, "rating_method": "sequential_elo", "raw_elo": 1956.8743249905033, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 81.32191846392729, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 152 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 41, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 12, "max_score": null, "measured_at": "2026-07-13T11:16:10Z", "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": 177, "rating_method": "sequential_elo", "raw_elo": 1835.462696509623, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 71.30162869957759, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 124 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 13, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 27, "max_score": null, "measured_at": "2026-07-13T11:15:47Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1825.7023228372973, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 70.48739385233826, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 136 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 38, "max_score": null, "measured_at": "2026-07-13T11:21:10Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Sol", "model_slug": "gpt-5-6-sol", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1776.8303231553305, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 66.44539299086682, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 134 }, { "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": 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": 32, "max_score": null, "measured_at": "2026-07-13T11:18:03Z", "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": 0, "rating_method": "sequential_elo", "raw_elo": 1755.6192364630972, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 64.68405752296643, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 126 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 48, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 48, "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": 46, "max_score": null, "measured_at": "2026-07-13T10:52:12Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1583.2566182888825, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.43571286891538, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 82 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 122, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "draws": 122, "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": 13, "max_score": null, "measured_at": "2026-07-13T11:06:43Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 177, "rating_method": "sequential_elo", "raw_elo": 1562.0402297802643, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 48.68798789794065, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 24, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 63, "max_score": null, "measured_at": "2026-07-13T10:47:47Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Qwen3.7 Plus", "model_slug": "qwen-qwen3-7-plus", "plugin_success_rate": null, "provider": "Alibaba", "provider_key": "qwen", "rank": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1555.18352725304, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 48.113903675728, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 89 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 42, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 42, "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": 54, "max_score": null, "measured_at": "2026-07-13T10:39:42Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Nemotron 3 Ultra 550B A55B", "model_slug": "nvidia-nemotron-3-ultra-550b-a55b", "plugin_success_rate": null, "provider": "NVIDIA", "provider_key": "nvidia", "rank": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1548.715871243637, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 47.57899061033618, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 3, "attempted_matches": 368, "capped_draws": 37, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 189, "draws": 37, "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": 123, "max_score": null, "measured_at": "2026-07-13T11:14:09Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 365, "rating_method": "sequential_elo", "raw_elo": 1553.474870529528, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 45.74532923505766, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 31.641683018769097, "unilateral_faults": 3, "wins": 205 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 34, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 76, "max_score": null, "measured_at": "2026-07-13T10:47:46Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1511.0191886358589, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.46125398063416, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 66 }, { "admitted_plugins": 1, "attempted_matches": 178, "capped_draws": 34, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 67, "max_score": null, "measured_at": "2026-07-13T10:29:32Z", "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": 175, "rating_method": "sequential_elo", "raw_elo": 1505.1064957058, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 43.965185356084454, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 74 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 95, "max_score": null, "measured_at": "2026-07-13T10:08:39Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1467.815676585255, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 40.888070274963766, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 79 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 28, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 28, "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": 77, "max_score": null, "measured_at": "2026-07-13T14:59:14Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1467.0402887330404, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 40.82394115426027, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 71 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 93, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 93, "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": 59, "max_score": null, "measured_at": "2026-07-13T11:17:43Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1447.806674913731, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.23320854391563, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 2, "attempted_matches": 364, "capped_draws": 123, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 184, "draws": 123, "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": 148, "max_score": null, "measured_at": "2026-07-13T11:16:10Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 360, "rating_method": "sequential_elo", "raw_elo": 1422.5622215473772, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 37.17297425067312, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 89 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 32, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 85, "max_score": null, "measured_at": "2026-07-13T09:10:02Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1415.7038044424205, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 36.578112968838866, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 59 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 81, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 81, "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": 66, "max_score": null, "measured_at": "2026-07-13T10:33:59Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1401.4664634495978, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 35.400601409407294, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 2, "attempted_matches": 195, "capped_draws": 43, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 102, "draws": 43, "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": 127, "max_score": null, "measured_at": "2026-07-13T10:52:17Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 190, "rating_method": "sequential_elo", "raw_elo": 1346.9560134273563, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 27.71826139168774, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 44.9403104781061, "unilateral_faults": 5, "wins": 20 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 37, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 37, "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": 102, "max_score": null, "measured_at": "2026-07-13T10:29:49Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-OSS 120B", "model_slug": "openai-gpt-oss-120b", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1266.7890787076983, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 24.261992212117935, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 2, "attempted_matches": 352, "capped_draws": 38, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 176, "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": 223, "max_score": null, "measured_at": "2026-07-13T11:05:30Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 352, "rating_method": "sequential_elo", "raw_elo": 1259.3008354454205, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.642670598228595, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 91 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 12, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 123, "max_score": null, "measured_at": "2026-07-13T10:03:12Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1256.888916122614, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.44319073155597, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 45, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 45, "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": 113, "max_score": null, "measured_at": "2026-07-13T10:33:36Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1233.5801986986205, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 21.515423164837383, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 27, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 124, "max_score": null, "measured_at": "2026-07-13T10:43:12Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT 5", "model_slug": "gpt-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1202.6591487315732, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.95807107329767, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugins": 4, "attempted_matches": 707, "capped_draws": 121, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 355, "draws": 121, "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": 516, "max_score": null, "measured_at": "2026-07-13T11:18:43Z", "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": 707, "rating_method": "sequential_elo", "raw_elo": 1157.921326676557, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.263222308732672, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 70 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 67, "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": "2026-07-13T08:41:52Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1750.9184381937966, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 59.44513946961022, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 94 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 111, "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": "2026-07-13T06:52:43Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1601.040803520877, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 32.87319708786287, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 89, "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": "2026-07-13T06:52:00Z", "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": 162, "rating_method": "sequential_elo", "raw_elo": 1594.983084343725, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 31.782257891449625, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 67 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 135, "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": "2026-07-13T04:24:13Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Gemini 3.5 Flash", "model_slug": "google-gemini-3-5-flash", "plugin_success_rate": null, "provider": "Google", "provider_key": "google", "rank": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1531.732358251298, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.585439689697196, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": 6, "max_score": null, "measured_at": "2026-07-13T03:10:22Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1499.4444060091091, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.877885447048715, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 155, "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": "2026-07-13T09:51:53Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1498.3417970308822, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.64863602866253, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 140, "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": "2026-07-13T03:33:22Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4", "model_slug": "gpt-5-4", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1497.5143688345588, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.518901175227816, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 3, "attempted_matches": 487, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 441, "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": 32, "max_score": null, "measured_at": "2026-07-13T10:05:47Z", "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": 487, "rating_method": "sequential_elo", "raw_elo": 1497.2723001644736, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.464677503373531, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 142, "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": "2026-07-13T03:19:46Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1494.7375477294534, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.026596031966744, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 3, "attempted_matches": 488, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 434, "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": 36, "max_score": null, "measured_at": "2026-07-13T10:08:15Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 488, "rating_method": "sequential_elo", "raw_elo": 1492.8057489565615, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.67840064525899, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 147, "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": "2026-07-13T03:14:46Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1492.0233169987628, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.562193816185417, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 3, "attempted_matches": 488, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 440, "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": 36, "max_score": null, "measured_at": "2026-07-13T10:05:40Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 488, "rating_method": "sequential_elo", "raw_elo": 1489.1504626235194, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.030351601501769, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 155, "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": "2026-07-13T03:20:50Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Qwen3.7 Plus", "model_slug": "qwen-qwen3-7-plus", "plugin_success_rate": null, "provider": "Alibaba", "provider_key": "qwen", "rank": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1488.9036829035151, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.009111045617562, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 138, "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": 18, "max_score": null, "measured_at": "2026-07-13T03:10:13Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1486.2616894159742, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 12.540709613495318, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 12, "max_score": null, "measured_at": "2026-07-13T02:44:51Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1480.7685811844883, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.56683145120459, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 150, "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": "2026-07-13T02:42:09Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Luna", "model_slug": "gpt-5-6-luna", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1479.88166278555, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.37582201210324, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 151, "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": "2026-07-13T02:39:53Z", "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": 162, "rating_method": "sequential_elo", "raw_elo": 1477.473010095113, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.94878978246065, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 151, "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": "2026-07-13T03:02:27Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1473.2591263768556, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.23547336764388, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 150, "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": "2026-07-13T03:17:22Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1471.6661923172385, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.95306063713581, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 152, "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": "2026-07-13T03:18:32Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1471.2175104960083, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.873513428324548, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 150, "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": "2026-07-13T03:26:22Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1465.213111145169, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 8.792181774741303, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 141, "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": "2026-07-13T03:49:55Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1457.8254805779036, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 7.482422021730727, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 2, "attempted_matches": 324, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 162, "draws": 282, "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": 37, "max_score": null, "measured_at": "2026-07-13T09:59:46Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 324, "rating_method": "sequential_elo", "raw_elo": 1453.7854276397609, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 6.7491967108184525, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 23, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 12, "draws": 4, "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": "2026-07-13T05:22:49Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 14, "rating_method": "sequential_elo", "raw_elo": 1573.2670768093667, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 67.15032789851486, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 85.34944487358055, "unilateral_faults": 3, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 28, "capped_draws": 1, "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": "GB2-03", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T18:28:37Z", "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": 19, "rating_method": "sequential_elo", "raw_elo": 1530.0797129244056, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 57.25721379782891, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 68.05339887498948, "unilateral_faults": 6, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 47, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 31, "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": 12, "max_score": null, "measured_at": "2026-07-13T05:22:45Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 44, "rating_method": "sequential_elo", "raw_elo": 1491.5723107308593, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 54.32702967567564, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 10 }, { "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": 19, "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": 7, "max_score": null, "measured_at": "2026-07-13T18:28:37Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 22, "rating_method": "sequential_elo", "raw_elo": 1495.139483110263, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 47.51485346996474, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 60.5072070285374, "unilateral_faults": 3, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 25, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 18, "draws": 5, "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": "2026-07-13T19:18:02Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Nex N2 Pro", "model_slug": "nex-agi-nex-n2-pro", "plugin_success_rate": null, "provider": "Nex AGI", "provider_key": "nex-agi", "rank": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 18, "rating_method": "sequential_elo", "raw_elo": 1484.3975960830628, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 41.07604676062133, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 70.95786693528086, "unilateral_faults": 3, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 20, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 6, "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": 0, "max_score": null, "measured_at": "2026-07-13T19:18:02Z", "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": 6, "rating_method": "sequential_elo", "raw_elo": 1542.3878676490287, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 40.594301511161184, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 100.0, "unilateral_faults": 11, "wins": 3 }, { "admitted_plugins": 3, "attempted_matches": 57, "capped_draws": 9, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 32, "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": 5, "max_score": null, "measured_at": "2026-07-13T18:48:15Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1512.3501346703968, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 40.42772895701176, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 92.50593750605547, "unilateral_faults": 16, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 13, "capped_draws": 2, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 8, "draws": 5, "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": 1, "max_score": null, "measured_at": "2026-07-13T19:18:02Z", "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": 8, "rating_method": "sequential_elo", "raw_elo": 1519.869789486925, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.021671024915825, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 100.0, "unilateral_faults": 4, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 40, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 17, "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": 7, "max_score": null, "measured_at": "2026-07-13T18:48:15Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 21, "rating_method": "sequential_elo", "raw_elo": 1469.7386447583692, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 38.321211372267925, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 62.850358177805205, "unilateral_faults": 4, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 10, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 4, "draws": 0, "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": 0, "max_score": null, "measured_at": "2026-07-13T18:48:15Z", "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": 4, "rating_method": "sequential_elo", "raw_elo": 1558.899979460019, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 36.823344296143375, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 100.0, "unilateral_faults": 3, "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": 1, "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": "GB2-03", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-08T11:20:47Z", "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": 17, "rating_method": "sequential_elo", "raw_elo": 1473.9712875944372, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 36.71408117019925, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 74.10113019775793, "unilateral_faults": 3, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 34, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 17, "draws": 16, "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": "2026-07-13T15:06:27Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 22, "rating_method": "sequential_elo", "raw_elo": 1456.417964127742, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.46308086219, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 60.5072070285374, "unilateral_faults": 3, "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": 4, "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": 0, "max_score": null, "measured_at": "2026-07-13T17:37:51Z", "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": 4, "rating_method": "sequential_elo", "raw_elo": 1548.1853629901475, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 33.21179336996703, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 100.0, "unilateral_faults": 9, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 14, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 4, "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": 1, "max_score": null, "measured_at": "2026-07-13T15:25:01Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 4, "rating_method": "sequential_elo", "raw_elo": 1515.5611346513658, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 22.215220379787834, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 100.0, "unilateral_faults": 5, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 9, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 6, "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": 3, "max_score": null, "measured_at": "2026-07-13T15:06:27Z", "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": 6, "rating_method": "sequential_elo", "raw_elo": 1456.317551717083, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.582779718067748, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 100.0, "unilateral_faults": 3, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 11, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 4, "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": 2, "max_score": null, "measured_at": "2026-07-13T18:48:15Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Luna", "model_slug": "gpt-5-6-luna", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 4, "rating_method": "sequential_elo", "raw_elo": 1469.3768449312888, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 6.647988945759312, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 100.0, "unilateral_faults": 4, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 17, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 3, "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": 2, "max_score": null, "measured_at": "2026-07-13T18:14:57Z", "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": 3, "rating_method": "sequential_elo", "raw_elo": 1470.872141220401, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 0.034968617309127016, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 100.0, "unilateral_faults": 9, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 95, "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": "2026-07-13T07:20:52Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1613.9588680555748, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 42.101358265742746, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugins": 2, "attempted_matches": 324, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 162, "draws": 201, "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": 46, "max_score": null, "measured_at": "2026-07-13T09:47:56Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 324, "rating_method": "sequential_elo", "raw_elo": 1548.0368493178066, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 30.733377137627382, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 77 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 97, "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": 26, "max_score": null, "measured_at": "2026-07-13T05:55:03Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1540.2910960595405, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 29.39958941518281, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugins": 3, "attempted_matches": 487, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 339, "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": 47, "max_score": null, "measured_at": "2026-07-13T09:15:55Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 487, "rating_method": "sequential_elo", "raw_elo": 1527.2539298459496, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 27.160132630433424, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 101 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 130, "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": "2026-07-13T06:10:45Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1525.012217087992, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 26.80142407302904, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 133, "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": "2026-07-13T05:29:14Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1519.6885679503296, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.88471298997989, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 112, "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": "2026-07-13T05:24:05Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Sonnet 5", "model_slug": "claude-sonnet-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1517.3293852666695, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.46214791748297, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 133, "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": "2026-07-13T05:22:03Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1515.3498397518797, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.12127809945343, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 125, "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": "2026-07-13T05:27:28Z", "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": 162, "rating_method": "sequential_elo", "raw_elo": 1514.9568544895735, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.03713437216872, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 135, "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": "2026-07-13T05:34:31Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-OSS 120B", "model_slug": "openai-gpt-oss-120b", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1513.2373943667817, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 24.77384670826449, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 121, "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": "2026-07-13T05:05:18Z", "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": 164, "rating_method": "sequential_elo", "raw_elo": 1507.7579377901347, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.83030620756496, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 102, "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": "2026-07-13T04:41:41Z", "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": 164, "rating_method": "sequential_elo", "raw_elo": 1505.1771434461737, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.38590374658337, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 126, "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": "2026-07-13T05:11:21Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1495.4302921877209, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 21.69121170153766, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 120, "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": "2026-07-13T04:48:59Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1492.984523164819, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 21.27006006064328, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 100, "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": 34, "max_score": null, "measured_at": "2026-07-13T04:40:15Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1491.0580523341491, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.954652743693853, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 125, "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": 16, "max_score": null, "measured_at": "2026-07-13T04:57:33Z", "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": 162, "rating_method": "sequential_elo", "raw_elo": 1488.4671596795529, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.475714903867996, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 135, "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": "2026-07-13T04:49:51Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1487.6486598737995, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.367569002063373, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 110, "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": "2026-07-13T04:39:23Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.5", "model_slug": "gpt-5-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1483.040140420163, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.541203899412803, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 37, "max_score": null, "measured_at": "2026-07-13T04:47:28Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT 5", "model_slug": "gpt-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1482.694962951085, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.514562210351176, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 2, "attempted_matches": 324, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 162, "draws": 139, "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": 90, "max_score": null, "measured_at": "2026-07-13T10:26:14Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 324, "rating_method": "sequential_elo", "raw_elo": 1480.1147879033615, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.037469899550587, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 95 }, { "admitted_plugins": 1, "attempted_matches": 65, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 42, "draws": 51, "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": "2026-07-08T14:07:19Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 58, "rating_method": "sequential_elo", "raw_elo": 1488.610341801933, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.928139079293686, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 21.344455490411935, "unilateral_faults": 7, "wins": 2 }, { "admitted_plugins": 3, "attempted_matches": 487, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 347, "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": 101, "max_score": null, "measured_at": "2026-07-13T10:26:31Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 487, "rating_method": "sequential_elo", "raw_elo": 1465.6068278537898, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.544748300487026, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 131, "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": "2026-07-13T10:04:50Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "DeepSeek V4 Flash", "model_slug": "deepseek-deepseek-v4-flash", "plugin_success_rate": null, "provider": "DeepSeek", "provider_key": "deepseek", "rank": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1465.3767636306457, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.49964108257143, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 118, "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": 31, "max_score": null, "measured_at": "2026-07-13T05:16:33Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1463.709311867719, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.228985797353044, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 128, "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": 25, "max_score": null, "measured_at": "2026-07-13T04:54:59Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1463.6398360355618, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.200549099667672, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 119, "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": "2026-07-13T05:57:35Z", "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": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1440.8685316555038, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 12.29589482449053, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 29, "max_score": null, "measured_at": "2026-07-13T05:58:01Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1434.2819346983647, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.16170917963443, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:17:41Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 2015.7806124353233, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 85.91160100452133, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 173 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:15:33Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 1950.2695886418971, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 80.83653200086476, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 164 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 36, "max_score": null, "measured_at": "2026-07-13T10:55:23Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 1823.3793315826204, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 71.00647939020519, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 156 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:07:35Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1762.2764333304506, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 66.27290316140129, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 144 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:06:41Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1742.2509150779815, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 64.72154766303917, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 125 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T10:52:14Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1730.7784959542173, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 63.83279161374329, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 134 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 61, "max_score": null, "measured_at": "2026-07-13T10:52:12Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1730.380099229294, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 63.80192824521784, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 131 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T10:35:59Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1695.2068025933097, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 61.07709054345052, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 124 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 63, "max_score": null, "measured_at": "2026-07-13T10:32:11Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1675.915942799595, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 59.58264825078116, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 129 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 74, "max_score": null, "measured_at": "2026-07-13T10:00:40Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1609.8170186446755, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 54.462035234390775, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 118 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T09:50:18Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 1600.3588618520066, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 53.729321935304526, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 117 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 76, "max_score": null, "measured_at": "2026-07-13T09:55:11Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 1595.0260967955364, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 53.3161983253421, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 116 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T09:23:11Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1586.088462104333, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 52.623809317190414, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 123 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 70, "max_score": null, "measured_at": "2026-07-13T09:13:53Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1576.1321527703371, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 51.85250467308791, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 122 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 90, "max_score": null, "measured_at": "2026-07-13T09:30:30Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4", "model_slug": "gpt-5-4", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1566.0421009894353, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 51.07083914455005, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 102 }, { "admitted_plugins": 2, "attempted_matches": 217, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 112, "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": "2026-07-13T11:15:40Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 208, "rating_method": "sequential_elo", "raw_elo": 1605.5251211638574, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.95899109613582, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 47.46252452815365, "unilateral_faults": 5, "wins": 140 }, { "admitted_plugins": 1, "attempted_matches": 193, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": 84, "max_score": null, "measured_at": "2026-07-13T09:21:41Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 193, "rating_method": "sequential_elo", "raw_elo": 1560.6505408344633, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.65891696822854, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 109 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 93, "max_score": null, "measured_at": "2026-07-13T08:50:28Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1509.421189981997, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 46.68447767783332, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 99 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 90, "max_score": null, "measured_at": "2026-07-13T08:44:34Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 1491.417483801888, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 45.289749800068414, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 102 }, { "admitted_plugins": 4, "attempted_matches": 595, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 302, "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": 319, "max_score": null, "measured_at": "2026-07-13T11:23:19Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 590, "rating_method": "sequential_elo", "raw_elo": 1491.5851365240233, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 43.714636706053675, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 23.731262264076825, "unilateral_faults": 5, "wins": 271 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 100, "max_score": null, "measured_at": "2026-07-13T08:24:30Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Step 3.7 Flash", "model_slug": "stepfun-step-3-7-flash", "plugin_success_rate": null, "provider": "StepFun", "provider_key": "stepfun", "rank": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1464.0972635440774, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 43.17328153297657, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 92 }, { "admitted_plugins": 3, "attempted_matches": 402, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 205, "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": 238, "max_score": null, "measured_at": "2026-07-13T10:25:36Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 397, "rating_method": "sequential_elo", "raw_elo": 1409.8533137151826, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 36.85168878311291, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 31.641683018769097, "unilateral_faults": 5, "wins": 159 }, { "admitted_plugins": 2, "attempted_matches": 384, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 192, "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": 250, "max_score": null, "measured_at": "2026-07-13T09:47:56Z", "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": 384, "rating_method": "sequential_elo", "raw_elo": 1355.1696649798114, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.734776879783745, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 134 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 116, "max_score": null, "measured_at": "2026-07-13T08:20:21Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 1353.774056292458, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.62666056621864, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 76 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 124, "max_score": null, "measured_at": "2026-07-13T08:46:31Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1343.6234989865052, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 33.84030773931548, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 68 }, { "admitted_plugins": 2, "attempted_matches": 386, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 194, "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": 299, "max_score": null, "measured_at": "2026-07-13T11:18:49Z", "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": 386, "rating_method": "sequential_elo", "raw_elo": 1162.486027042327, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.813515423128983, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 87 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 157, "max_score": null, "measured_at": "2026-07-13T10:29:10Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 1157.1332982965882, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.39311118822044, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 155, "max_score": null, "measured_at": "2026-07-13T10:25:36Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1149.9880919470363, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.839579688183345, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 181, "max_score": null, "measured_at": "2026-07-13T10:57:55Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 977.0384206037112, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 5.4413534752207235, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 5, "max_score": null, "measured_at": "2026-07-13T11:18:45Z", "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": 177, "rating_method": "sequential_elo", "raw_elo": 2113.172705854929, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 100.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 163 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": "2026-07-13T11:17:11Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 2021.3042300854584, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 92.37554944921584, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 152 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 22, "max_score": null, "measured_at": "2026-07-13T11:18:08Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 2013.227461625624, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 91.70584983423836, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 152 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 13, "max_score": null, "measured_at": "2026-07-13T11:16:01Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 2011.625745950398, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 91.5730407316453, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 151 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 20, "max_score": null, "measured_at": "2026-07-13T11:14:15Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Fable 5", "model_slug": "claude-fable-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1951.6074811596209, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 86.59651961160996, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 148 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 33, "max_score": null, "measured_at": "2026-07-13T11:16:59Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1894.7354687831812, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 81.88087560362533, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 136 }, { "admitted_plugins": 2, "attempted_matches": 361, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 181, "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": 53, "max_score": null, "measured_at": "2026-07-13T11:18:18Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 357, "rating_method": "sequential_elo", "raw_elo": 1892.7238164979417, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 81.73143238427392, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 284 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": "2026-07-13T11:15:05Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Luna", "model_slug": "gpt-5-6-luna", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1809.9810988197512, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 74.85331634964449, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 130 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 44, "max_score": null, "measured_at": "2026-07-13T11:05:20Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1762.1928177551893, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 70.89086607159972, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 130 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 63, "max_score": null, "measured_at": "2026-07-13T11:05:03Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Nemotron 3 Ultra 550B A55B", "model_slug": "nvidia-nemotron-3-ultra-550b-a55b", "plugin_success_rate": null, "provider": "NVIDIA", "provider_key": "nvidia", "rank": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1693.901124469253, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 65.22833892015394, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 106 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 61, "max_score": null, "measured_at": "2026-07-13T10:52:13Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1639.345101131601, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 60.70472926047103, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 102 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 72, "max_score": null, "measured_at": "2026-07-13T10:04:33Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1555.0824415117218, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 53.71794104374275, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 90 }, { "admitted_plugins": 4, "attempted_matches": 545, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 276, "draws": 16, "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": 222, "max_score": null, "measured_at": "2026-07-13T11:06:49Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4 Nano", "model_slug": "gpt-5-4-nano", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 540, "rating_method": "sequential_elo", "raw_elo": 1562.9244662084404, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 52.691719485250296, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 23.731262264076825, "unilateral_faults": 5, "wins": 302 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 83, "max_score": null, "measured_at": "2026-07-13T09:29:34Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1518.8008146816196, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.709585457011585, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 86 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 75, "max_score": null, "measured_at": "2026-07-13T09:54:41Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 177, "rating_method": "sequential_elo", "raw_elo": 1511.5014810101663, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.11136079666177, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 90 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 74, "max_score": null, "measured_at": "2026-07-13T09:26:41Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 177, "rating_method": "sequential_elo", "raw_elo": 1510.0804882823834, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 49.99353665852848, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 95 }, { "admitted_plugins": 2, "attempted_matches": 193, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 100, "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": 82, "max_score": null, "measured_at": "2026-07-13T10:07:26Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1530.077498296977, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 48.29169777153082, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 47.46252452815365, "unilateral_faults": 5, "wins": 94 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 94, "max_score": null, "measured_at": "2026-07-13T10:25:36Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Sonnet 5", "model_slug": "claude-sonnet-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1438.558704040331, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.05616820620246, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 78 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 114, "max_score": null, "measured_at": "2026-07-13T10:56:42Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1281.0925805566576, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 30.999584648874865, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 61 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 113, "max_score": null, "measured_at": "2026-07-13T10:53:21Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1249.5659613788737, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.38549897464753, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 63 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 134, "max_score": null, "measured_at": "2026-07-13T10:57:42Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1225.2173017628277, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 26.36658657779288, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 129, "max_score": null, "measured_at": "2026-07-13T11:16:31Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1175.1745877661265, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 22.21720598545791, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 137, "max_score": null, "measured_at": "2026-07-13T11:18:06Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1173.38593216378, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 22.0688964264832, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 135, "max_score": null, "measured_at": "2026-07-13T11:16:25Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1155.29572221864, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.568914509783472, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 137, "max_score": null, "measured_at": "2026-07-13T11:13:11Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Gemma 4 31B", "model_slug": "google-gemma-4-31b-it", "plugin_success_rate": null, "provider": "Google", "provider_key": "google", "rank": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1144.2132883540614, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.649994804578235, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 130, "max_score": null, "measured_at": "2026-07-13T11:14:05Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1133.2351915876884, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.739726395351543, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 131, "max_score": null, "measured_at": "2026-07-13T11:14:31Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1132.7350894614683, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.698259538520816, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 2, "attempted_matches": 355, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 179, "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": 291, "max_score": null, "measured_at": "2026-07-13T11:18:50Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "DeepSeek V4 Flash", "model_slug": "deepseek-deepseek-v4-flash", "plugin_success_rate": null, "provider": "DeepSeek", "provider_key": "deepseek", "rank": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 355, "rating_method": "sequential_elo", "raw_elo": 1127.2314312945098, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.252344927225373, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 62 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 141, "max_score": null, "measured_at": "2026-07-13T11:16:43Z", "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": 29, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1074.5271388747817, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.87184383892639, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T11:16:50Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Fable 5", "model_slug": "claude-fable-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1953.181211186572, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 84.36077496947715, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 158 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 29, "max_score": null, "measured_at": "2026-07-13T11:17:21Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 1884.3584188699683, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 79.21328749427038, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 153 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T11:14:17Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1831.9116897038568, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 75.29062070888055, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 142 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 54, "max_score": null, "measured_at": "2026-07-13T11:17:56Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1778.1423812549197, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 71.26903378287814, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 128 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T11:14:26Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1752.039738336122, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 69.31672956836447, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 132 }, { "admitted_plugins": 1, "attempted_matches": 183, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T11:13:28Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT 5", "model_slug": "gpt-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 183, "rating_method": "sequential_elo", "raw_elo": 1735.7319944025955, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 68.10303654582466, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 132 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T11:23:19Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 1717.941915249386, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 66.76643901253581, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 136 }, { "admitted_plugins": 1, "attempted_matches": 183, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T11:02:36Z", "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": 183, "rating_method": "sequential_elo", "raw_elo": 1694.3564993288446, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 65.00842449211945, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 129 }, { "admitted_plugins": 3, "attempted_matches": 390, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 199, "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": 102, "max_score": null, "measured_at": "2026-07-13T11:18:29Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 379, "rating_method": "sequential_elo", "raw_elo": 1703.0673274688045, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 63.63124555669186, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 31.641683018769097, "unilateral_faults": 5, "wins": 277 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 84, "max_score": null, "measured_at": "2026-07-13T10:53:23Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1621.1705023347804, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 59.528580460612154, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 98 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 66, "max_score": null, "measured_at": "2026-07-13T11:04:15Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 1621.1486703944136, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 59.526947576565824, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 116 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 72, "max_score": null, "measured_at": "2026-07-13T11:04:23Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 1601.086003724768, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 58.0263934443509, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 110 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 82, "max_score": null, "measured_at": "2026-07-13T11:03:56Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1570.2651551058498, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 55.72119880023805, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 100 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 84, "max_score": null, "measured_at": "2026-07-13T10:30:54Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1568.1544613440951, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 55.56333293433932, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 98 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 96, "max_score": null, "measured_at": "2026-07-13T09:53:58Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 1482.8379416878386, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 49.18222426995193, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 86 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 108, "max_score": null, "measured_at": "2026-07-13T09:49:00Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1423.92500364893, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.775928034718326, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 74 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 106, "max_score": null, "measured_at": "2026-07-13T09:55:05Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Luna", "model_slug": "gpt-5-6-luna", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1413.788029156669, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.0177497121161, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 76 }, { "admitted_plugins": 3, "attempted_matches": 384, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 197, "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": 210, "max_score": null, "measured_at": "2026-07-13T10:41:05Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4 Mini", "model_slug": "gpt-5-4-mini", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 379, "rating_method": "sequential_elo", "raw_elo": 1428.2445475280326, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 43.17494898897335, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 29.960206985404067, "unilateral_faults": 5, "wins": 169 }, { "admitted_plugins": 2, "attempted_matches": 365, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 185, "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": 222, "max_score": null, "measured_at": "2026-07-13T11:06:32Z", "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": 365, "rating_method": "sequential_elo", "raw_elo": 1383.6457361670127, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 41.76631544139825, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 143 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 107, "max_score": null, "measured_at": "2026-07-13T09:48:51Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1381.410667501206, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 41.59613823731507, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 75 }, { "admitted_plugins": 2, "attempted_matches": 196, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 104, "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": 119, "max_score": null, "measured_at": "2026-07-13T09:58:18Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "DeepSeek V4 Flash", "model_slug": "deepseek-deepseek-v4-flash", "plugin_success_rate": null, "provider": "DeepSeek", "provider_key": "deepseek", "rank": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 195, "rating_method": "sequential_elo", "raw_elo": 1408.5854057885842, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 40.58862492867081, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 47.46252452815365, "unilateral_faults": 1, "wins": 76 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 121, "max_score": null, "measured_at": "2026-07-13T10:26:05Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1350.700990355189, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.29925848053965, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 61 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 119, "max_score": null, "measured_at": "2026-07-13T10:26:40Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1341.347023577133, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 38.59964393116125, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 63 }, { "admitted_plugins": 4, "attempted_matches": 564, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 287, "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": 389, "max_score": null, "measured_at": "2026-07-13T11:17:52Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 560, "rating_method": "sequential_elo", "raw_elo": 1263.3867857170294, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 31.250239151073856, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 23.731262264076825, "unilateral_faults": 4, "wins": 171 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 123, "max_score": null, "measured_at": "2026-07-13T11:02:13Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1231.8088563680926, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 30.40691700471232, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 59 }, { "admitted_plugins": 1, "attempted_matches": 183, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": null, "is_recent_addition": false, "last_measured_at": null, "losses": 143, "max_score": null, "measured_at": "2026-07-13T11:02:13Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Grok Build 0.1", "model_slug": "x-ai-grok-build-0-1", "plugin_success_rate": null, "provider": "xAI", "provider_key": "x-ai", "rank": 26, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 183, "rating_method": "sequential_elo", "raw_elo": 1204.7719636992797, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.390754961728646, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 163, "max_score": null, "measured_at": "2026-07-13T11:13:17Z", "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": 27, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1023.8789974673142, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.855145442036957, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 168, "max_score": null, "measured_at": "2026-07-13T11:17:36Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 945.9132596935534, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.023826409826338, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-08", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T11:04:20Z", "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": 189, "rating_method": "sequential_elo", "raw_elo": 1970.0641033155896, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 80.6996391732329, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 178 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 14, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "draws": 14, "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": "2026-07-13T11:06:34Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1947.083957209489, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 78.21558607258677, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 154 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 21, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "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": "2026-07-13T10:25:36Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1767.1268182403671, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 58.83595172966278, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 142 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 89, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "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": 27, "max_score": null, "measured_at": "2026-07-13T10:37:03Z", "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": 186, "rating_method": "sequential_elo", "raw_elo": 1552.067087925525, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 35.64126006400562, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 70 }, { "admitted_plugins": 3, "attempted_matches": 561, "capped_draws": 219, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 281, "draws": 219, "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": 161, "max_score": null, "measured_at": "2026-07-13T11:14:33Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 561, "rating_method": "sequential_elo", "raw_elo": 1534.1212585814792, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 33.71621527419026, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 181 }, { "admitted_plugins": 1, "attempted_matches": 190, "capped_draws": 76, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "draws": 76, "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": "2026-07-13T09:18:44Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 190, "rating_method": "sequential_elo", "raw_elo": 1523.3706998722455, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 32.58279423932358, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 75 }, { "admitted_plugins": 1, "attempted_matches": 190, "capped_draws": 101, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "draws": 101, "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": 42, "max_score": null, "measured_at": "2026-07-13T09:47:56Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1508.2797586658528, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 30.948758875345156, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 1, "wins": 46 }, { "admitted_plugins": 1, "attempted_matches": 89, "capped_draws": 23, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 53, "draws": 23, "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": "2026-07-12T07:18:18Z", "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": 83, "rating_method": "sequential_elo", "raw_elo": 1515.3168846424774, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 30.131321176688537, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 10.804472558998102, "unilateral_faults": 6, "wins": 22 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 107, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 107, "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": "2026-07-13T11:05:29Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1485.3601398335422, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.454508438462973, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugins": 1, "attempted_matches": 190, "capped_draws": 79, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 64, "max_score": null, "measured_at": "2026-07-13T09:49:11Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 190, "rating_method": "sequential_elo", "raw_elo": 1480.5657308160917, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 27.971150478895108, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugins": 3, "attempted_matches": 563, "capped_draws": 346, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 283, "draws": 346, "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": 137, "max_score": null, "measured_at": "2026-07-13T11:13:29Z", "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": 563, "rating_method": "sequential_elo", "raw_elo": 1438.9778296664265, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.471310902314137, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 152, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 152, "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": 34, "max_score": null, "measured_at": "2026-07-13T10:57:06Z", "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": 186, "rating_method": "sequential_elo", "raw_elo": 1416.9867323704073, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 21.088218849678245, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 127, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 127, "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": 45, "max_score": null, "measured_at": "2026-07-13T11:07:08Z", "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": 186, "rating_method": "sequential_elo", "raw_elo": 1407.0276642403533, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.01526691408883, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 132, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 132, "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": "2026-07-13T10:37:05Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1405.431006653321, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.868227433674654, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 127, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 127, "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": 45, "max_score": null, "measured_at": "2026-07-13T11:06:28Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1404.395730339692, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.73171241519593, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 132, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 132, "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": 45, "max_score": null, "measured_at": "2026-07-13T11:15:41Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1391.1774857786118, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.32434758125932, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 2, "attempted_matches": 375, "capped_draws": 191, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 188, "draws": 191, "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": 138, "max_score": null, "measured_at": "2026-07-13T11:07:46Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 375, "rating_method": "sequential_elo", "raw_elo": 1388.505901557898, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.032358403988177, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 129, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "draws": 129, "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": 51, "max_score": null, "measured_at": "2026-07-13T11:15:55Z", "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": 189, "rating_method": "sequential_elo", "raw_elo": 1387.7628352400186, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 17.96472617545748, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 129, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 129, "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": "2026-07-13T11:16:26Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Minimax M3", "model_slug": "minimax-minimax-m3", "plugin_success_rate": null, "provider": "MiniMax", "provider_key": "minimax", "rank": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1386.9649746432217, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 17.85378941887912, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 3, "attempted_matches": 402, "capped_draws": 248, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 208, "draws": 248, "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": 105, "max_score": null, "measured_at": "2026-07-13T11:18:39Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 394, "rating_method": "sequential_elo", "raw_elo": 1404.027846907638, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 17.458145034751666, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 23.65262231176029, "unilateral_faults": 5, "wins": 41 }, { "admitted_plugins": 1, "attempted_matches": 187, "capped_draws": 132, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "draws": 132, "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": "2026-07-13T11:14:46Z", "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": 187, "rating_method": "sequential_elo", "raw_elo": 1383.0665226852393, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 17.44217760975673, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 2, "attempted_matches": 375, "capped_draws": 247, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 189, "draws": 247, "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": 110, "max_score": null, "measured_at": "2026-07-13T11:15:19Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 375, "rating_method": "sequential_elo", "raw_elo": 1379.838515181817, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 17.098567323610556, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 115, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 115, "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": 66, "max_score": null, "measured_at": "2026-07-13T11:18:07Z", "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": 186, "rating_method": "sequential_elo", "raw_elo": 1369.61060669953, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.984096147083603, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 126, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 126, "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": 60, "max_score": null, "measured_at": "2026-07-13T11:13:55Z", "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": 186, "rating_method": "sequential_elo", "raw_elo": 1365.3921680716376, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.52961769268853, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 127, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "draws": 127, "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": 51, "max_score": null, "measured_at": "2026-07-13T11:00:06Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1363.4289818338318, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.33482982433031, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 187, "capped_draws": 132, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "draws": 132, "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": 47, "max_score": null, "measured_at": "2026-07-13T11:17:07Z", "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": 187, "rating_method": "sequential_elo", "raw_elo": 1356.976545254924, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.6313431604106, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 128, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 128, "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": 58, "max_score": null, "measured_at": "2026-07-13T11:15:30Z", "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": 186, "rating_method": "sequential_elo", "raw_elo": 1344.363634400764, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.264083848544765, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 37, "capped_draws": 5, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 36, "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": "2026-07-08T14:06:51Z", "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": 28, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 36, "rating_method": "sequential_elo", "raw_elo": 1276.2559408675754, "reasoning_level": "Medium", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "medium", "source": "public_redacted_snapshot", "track_id": "full_freedom/medium" }, "provider_route": "unknown_legacy", "reasoning_bucket": "medium", "reasoning_bucket_label": "Medium reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "medium" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 1.9931136856735752, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/medium", "track_name": "Medium variants", "uncertainty": 38.449493652678655, "unilateral_faults": 1, "wins": 1 }, { "admitted_plugins": 8, "attempted_matches": 1276, "capped_draws": 125, "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-2026-07-12": 10 }, "run_count": 8, "token_priced_attempt_count": 10, "total": 0.7485199999999999 }, "codegen_evaluated_cells": 8, "conditional_success_score": 49.29725888272484, "contributing_entrants": null, "distinct_rated_opponents": 640, "draws": 415, "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": "2026-07-13T17:37:51Z", "losses": 282, "max_score": 93.92197991363965, "measured_at": null, "min_score": 13.62877706153271, "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1258, "rating_method": "sequential_elo", "raw_elo": 1638.1199975892866, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 49.29725888272484, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 9, "wins": 561 }, { "admitted_plugins": 8, "attempted_matches": 1264, "capped_draws": 111, "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-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 0.97393 }, "codegen_evaluated_cells": 8, "conditional_success_score": 45.948850737620106, "contributing_entrants": null, "distinct_rated_opponents": 634, "draws": 370, "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": "2026-07-13T17:59:25Z", "losses": 343, "max_score": 78.8982296737467, "measured_at": null, "min_score": 9.13197672529834, "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1252, "rating_method": "sequential_elo", "raw_elo": 1584.8470076121366, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 45.948850737620106, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 4, "wins": 539 }, { "admitted_plugins": 7, "attempted_matches": 1241, "capped_draws": 35, "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-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 1.262825 }, "codegen_evaluated_cells": 8, "conditional_success_score": 44.78300955956154, "contributing_entrants": null, "distinct_rated_opponents": 622, "draws": 303, "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": "2026-07-13T11:07:15Z", "losses": 394, "max_score": 80.92699793368016, "measured_at": null, "min_score": 10.536099280916575, "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1241, "rating_method": "sequential_elo", "raw_elo": 1584.8108268945596, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 43.312703200127544, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 0, "wins": 544 }, { "admitted_plugins": 8, "attempted_matches": 1269, "capped_draws": 159, "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": 0.07806, "mean": 0.06121625, "median": 0.061152, "min": 0.049788, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 0.4897299999999999 }, "codegen_evaluated_cells": 8, "conditional_success_score": 38.947734987153694, "contributing_entrants": null, "distinct_rated_opponents": 630, "draws": 445, "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": "2026-07-13T19:18:02Z", "losses": 362, "max_score": 62.65785807563824, "measured_at": null, "min_score": 11.421558133782472, "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1251, "rating_method": "sequential_elo", "raw_elo": 1534.219935928596, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 38.947734987153694, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 5, "wins": 444 }, { "admitted_plugins": 6, "attempted_matches": 925, "capped_draws": 57, "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": 41.2811008153348, "contributing_entrants": null, "distinct_rated_opponents": 464, "draws": 210, "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": "2026-07-13T19:18:02Z", "losses": 358, "max_score": 60.293433204479186, "measured_at": null, "min_score": 12.76276880459896, "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 914, "rating_method": "sequential_elo", "raw_elo": 1528.6435719264146, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 38.41639300783421, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 4, "wins": 346 }, { "admitted_plugins": 7, "attempted_matches": 1092, "capped_draws": 203, "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": 38.62543981510385, "contributing_entrants": null, "distinct_rated_opponents": 550, "draws": 368, "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": "2026-07-13T11:13:38Z", "losses": 358, "max_score": 75.9025597410182, "measured_at": null, "min_score": 10.124210580685428, "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1078, "rating_method": "sequential_elo", "raw_elo": 1491.0037867490844, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 37.35729749160615, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 7, "wins": 352 }, { "admitted_plugins": 8, "attempted_matches": 1251, "capped_draws": 73, "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-2026-07-12": 9 }, "run_count": 9, "token_priced_attempt_count": 9, "total": 1.069485 }, "codegen_evaluated_cells": 9, "conditional_success_score": 38.30307049865906, "contributing_entrants": null, "distinct_rated_opponents": 621, "draws": 333, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:18:17Z", "losses": 377, "max_score": 61.59221622927624, "measured_at": null, "min_score": 12.279638610710084, "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1239, "rating_method": "sequential_elo", "raw_elo": 1538.9197284923318, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 37.191651116449, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 4, "wins": 529 }, { "admitted_plugins": 8, "attempted_matches": 1268, "capped_draws": 130, "codegen_cost_usd": { "admitted_cell_count": 8, "cell_count": 8, "cost_basis_counts": { "local_standard_estimate": 11 }, "evidence_basis": "Standard list-price estimate", "max": 0.094594, "mean": 0.0571955, "median": 0.043012, "min": 0.032534, "pricing_table_versions": { "boardgame-list-prices-2026-07-12": 11 }, "run_count": 8, "token_priced_attempt_count": 11, "total": 0.4575640000000001 }, "codegen_evaluated_cells": 8, "conditional_success_score": 36.54444523651211, "contributing_entrants": null, "distinct_rated_opponents": 639, "draws": 416, "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": "2026-07-13T11:07:36Z", "losses": 447, "max_score": 58.420430590270925, "measured_at": null, "min_score": 9.661510668959371, "model_code_failure_rate": 0.0, "model_code_failures": 0, "model_display_name": "GPT 4.1", "model_slug": "gpt-4-1", "plugin_success_rate": 1.0, "provider": "OpenAI", "provider_key": "openai", "rank": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1257, "rating_method": "sequential_elo", "raw_elo": 1487.165424185781, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 3, "repaired_rate": 0.375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 36.54444523651211, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 3, "wins": 394 }, { "admitted_plugins": 17, "attempted_matches": 2875, "capped_draws": 340, "codegen_cost_usd": { "admitted_cell_count": 17, "cell_count": 8, "cost_basis_counts": { "provider_reported": 37 }, "evidence_basis": "Provider-reported", "failed_cell_count": 7, "max": 0.005169185000000001, "mean": 0.002871050658333333, "median": 0.0023354879666666667, "min": 0.00169122, "recorded_attempt_count": 37, "run_count": 24, "total": 0.0689052158 }, "codegen_evaluated_cells": 24, "conditional_success_score": 39.74564768749891, "contributing_entrants": null, "distinct_rated_opponents": 1439, "draws": 733, "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": "2026-07-13T11:18:27Z", "losses": 1350, "max_score": 44.51492353136073, "measured_at": null, "min_score": 35.26480634810233, "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 2864, "rating_method": "sequential_elo", "raw_elo": 1408.906700122149, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 5, "repaired_rate": 0.20833333333333337, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 36.46271462621648, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 9, "wins": 781 }, { "admitted_plugins": 28, "attempted_matches": 4353, "capped_draws": 225, "codegen_cost_usd": { "admitted_cell_count": 28, "cell_count": 8, "cost_basis_counts": { "local_list_price_estimate": 1, "provider_reported": 48 }, "evidence_basis": "Mixed: Provider-reported + Standard list-price estimate", "failed_cell_count": 4, "max": 0.0370864994, "mean": 0.02452730386875, "median": 0.023468922225, "min": 0.0140238704, "recorded_attempt_count": 48, "run_count": 32, "token_priced_attempt_count": 1, "total": 0.7848737238 }, "codegen_evaluated_cells": 32, "conditional_success_score": 37.57846636346578, "contributing_entrants": null, "distinct_rated_opponents": 2191, "draws": 1173, "entry_count": 28, "failed_game_aliases": [ "GB2-02", "GB2-03", "GB2-07", "GB2-08" ], "first_pass_admitted": 16, "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": "2026-07-13T18:48:15Z", "losses": 1494, "max_score": 49.07869792911936, "measured_at": null, "min_score": 23.621129291107756, "model_code_failure_rate": 0.125, "model_code_failures": 4, "model_display_name": "GLM-5.2", "model_slug": "z-ai-glm-5-2", "plugin_success_rate": 0.875, "provider": "Zhipu", "provider_key": "z-ai", "rank": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 4308, "rating_method": "sequential_elo", "raw_elo": 1531.1078278859848, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 12, "repaired_rate": 0.375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 36.34469805232771, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 22, "wins": 1641 }, { "admitted_plugins": 7, "attempted_matches": 1002, "capped_draws": 166, "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": 34.81236948125838, "contributing_entrants": null, "distinct_rated_opponents": 508, "draws": 233, "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": "2026-07-13T11:17:55Z", "losses": 358, "max_score": 68.2973627113312, "measured_at": null, "min_score": 10.794214509222783, "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 986, "rating_method": "sequential_elo", "raw_elo": 1485.246091313927, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 33.6694170817064, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 9, "wins": 395 }, { "admitted_plugins": 6, "attempted_matches": 929, "capped_draws": 47, "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": 34.37636459588008, "contributing_entrants": null, "distinct_rated_opponents": 468, "draws": 189, "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": "2026-07-13T10:52:32Z", "losses": 423, "max_score": 55.02211698080321, "measured_at": null, "min_score": 0.0, "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 916, "rating_method": "sequential_elo", "raw_elo": 1429.4342497077123, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.2857142857142857, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 33.076781883437384, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 3, "wins": 304 }, { "admitted_plugins": 8, "attempted_matches": 1248, "capped_draws": 186, "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-2026-07-12": 10 }, "run_count": 9, "token_priced_attempt_count": 10, "total": 0.6063375 }, "codegen_evaluated_cells": 9, "conditional_success_score": 34.05639297351176, "contributing_entrants": null, "distinct_rated_opponents": 623, "draws": 479, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T16:11:38Z", "losses": 420, "max_score": 54.92953555759788, "measured_at": null, "min_score": 14.71302727158694, "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1241, "rating_method": "sequential_elo", "raw_elo": 1471.9612833739554, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 1, "repaired_rate": 0.1111111111111111, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 33.06819712534213, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 3, "wins": 342 }, { "admitted_plugins": 7, "attempted_matches": 1089, "capped_draws": 257, "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-2026-07-12": 8 }, "run_count": 8, "token_priced_attempt_count": 8, "total": 1.13802 }, "codegen_evaluated_cells": 8, "conditional_success_score": 32.87543335559842, "contributing_entrants": null, "distinct_rated_opponents": 548, "draws": 539, "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": "2026-07-13T14:18:39Z", "losses": 281, "max_score": 54.81592371456018, "measured_at": null, "min_score": 9.168698365108394, "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1080, "rating_method": "sequential_elo", "raw_elo": 1493.3565913362868, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 0, "repaired_rate": 0.0, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 31.796074035908287, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 8, "wins": 260 }, { "admitted_plugins": 7, "attempted_matches": 1097, "capped_draws": 154, "codegen_cost_usd": { "admitted_cell_count": 7, "cell_count": 8, "cost_basis_counts": { "provider_reported": 14 }, "evidence_basis": "Provider-reported", "failed_cell_count": 2, "max": 0.13485595, "mean": 0.03179205625, "median": 0.0158481, "min": 0.0111232, "recorded_attempt_count": 14, "run_count": 9, "total": 0.3891924 }, "codegen_evaluated_cells": 9, "conditional_success_score": 33.48108617544016, "contributing_entrants": null, "distinct_rated_opponents": 547, "draws": 283, "entry_count": 7, "failed_game_aliases": [ "GB2-02", "GB2-07" ], "first_pass_admitted": 5, "first_pass_rate": 0.5555555555555556, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T18:14:57Z", "losses": 490, "max_score": 64.09572011977573, "measured_at": null, "min_score": 12.512381512184156, "model_code_failure_rate": 0.2222222222222222, "model_code_failures": 2, "model_display_name": "Nemotron 3 Ultra 550B A55B", "model_slug": "nvidia-nemotron-3-ultra-550b-a55b", "plugin_success_rate": 0.7777777777777778, "provider": "NVIDIA", "provider_key": "nvidia", "rank": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1085, "rating_method": "sequential_elo", "raw_elo": 1400.3841885227164, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.2222222222222222, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 31.442235871587773, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 9, "wins": 312 }, { "admitted_plugins": 6, "attempted_matches": 973, "capped_draws": 146, "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": 30.719102136050925, "contributing_entrants": null, "distinct_rated_opponents": 451, "draws": 389, "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": "2026-07-13T18:48:15Z", "losses": 258, "max_score": 78.86564479729775, "measured_at": null, "min_score": 3.928336942357347, "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 889, "rating_method": "sequential_elo", "raw_elo": 1481.1182426096595, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 28.587345715062675, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 3, "wins": 242 }, { "admitted_plugins": 24, "attempted_matches": 3286, "capped_draws": 442, "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-2026-07-12": 29 }, "run_count": 24, "token_priced_attempt_count": 29, "total": 0.4149345000000001 }, "codegen_evaluated_cells": 24, "conditional_success_score": 25.597809333588906, "contributing_entrants": null, "distinct_rated_opponents": 1667, "draws": 1249, "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": "2026-07-13T17:59:25Z", "losses": 1496, "max_score": 45.38475762538517, "measured_at": null, "min_score": 9.599170646265678, "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 3256, "rating_method": "sequential_elo", "raw_elo": 1368.073570250796, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 5, "repaired_rate": 0.20833333333333337, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 25.597809333588906, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 30, "wins": 511 }, { "admitted_plugins": 25, "attempted_matches": 3638, "capped_draws": 503, "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-2026-07-12": 56 }, "run_count": 32, "token_priced_attempt_count": 56, "total": 0.28794675 }, "codegen_evaluated_cells": 32, "conditional_success_score": 24.45520203265773, "contributing_entrants": null, "distinct_rated_opponents": 1828, "draws": 1315, "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": "2026-07-13T19:18:02Z", "losses": 1449, "max_score": 34.958989185678846, "measured_at": null, "min_score": 8.830356337516129, "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 3600, "rating_method": "sequential_elo", "raw_elo": 1403.446631527928, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 15, "repaired_rate": 0.46875, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 22.99157710151633, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 16, "wins": 836 }, { "admitted_plugins": 19, "attempted_matches": 2916, "capped_draws": 275, "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": 22.91569280210852, "contributing_entrants": null, "distinct_rated_opponents": 1479, "draws": 953, "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": "2026-07-13T19:18:02Z", "losses": 1407, "max_score": 34.15933294953593, "measured_at": null, "min_score": 12.636240270675255, "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 2894, "rating_method": "sequential_elo", "raw_elo": 1361.7817059097324, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 5, "repaired_rate": 0.20833333333333337, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 21.61566402629856, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 13, "wins": 534 }, { "admitted_plugins": 6, "attempted_matches": 1076, "capped_draws": 155, "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": 21.582884603762555, "contributing_entrants": null, "distinct_rated_opponents": 538, "draws": 281, "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": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:18:03Z", "losses": 604, "max_score": 38.16566067067517, "measured_at": null, "min_score": 13.28495376492924, "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1076, "rating_method": "sequential_elo", "raw_elo": 1274.1875697355829, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 1, "repaired_rate": 0.14285714285714285, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 20.766953540503557, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 0, "wins": 191 }, { "admitted_plugins": 6, "attempted_matches": 1053, "capped_draws": 33, "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": 20.39523540138827, "contributing_entrants": null, "distinct_rated_opponents": 527, "draws": 312, "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": "2026-07-13T11:18:54Z", "losses": 576, "max_score": 39.79517533017037, "measured_at": null, "min_score": 9.082592792115568, "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1052, "rating_method": "sequential_elo", "raw_elo": 1284.49012654842, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.2222222222222222, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 18.42917557278888, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 0, "wins": 164 }, { "admitted_plugins": 8, "attempted_matches": 1256, "capped_draws": 164, "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-2026-07-12": 9 }, "run_count": 8, "token_priced_attempt_count": 9, "total": 0.175742 }, "codegen_evaluated_cells": 8, "conditional_success_score": 11.614618741665524, "contributing_entrants": null, "distinct_rated_opponents": 626, "draws": 435, "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": "2026-07-13T18:14:57Z", "losses": 732, "max_score": 21.507682567414136, "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 1244, "rating_method": "sequential_elo", "raw_elo": 1220.8336508088682, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 1, "repaired_rate": 0.125, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 11.614618741665524, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 5, "wins": 77 }, { "admitted_plugins": 5, "attempted_matches": 890, "capped_draws": 40, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 13 }, "evidence_basis": "Provider-reported", "failed_cell_count": 3, "max": 0.00870475, "mean": 0.005883593750000001, "median": 0.006313125, "min": 0.003432, "recorded_attempt_count": 13, "run_count": 8, "total": 0.04706874999999999 }, "codegen_evaluated_cells": 8, "conditional_success_score": 11.324732813184706, "contributing_entrants": null, "distinct_rated_opponents": 445, "draws": 191, "entry_count": 5, "failed_game_aliases": [ "GB2-03", "GB2-04", "GB2-08" ], "first_pass_admitted": 3, "first_pass_rate": 0.375, "first_seen_at": null, "game_alias": null, "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_seconds": null, "stream_progress_event_count": null }, "infra_excluded_game_aliases": [], "infra_failures_excluded": 0, "is_recent_addition": false, "last_measured_at": "2026-07-13T11:18:28Z", "losses": 614, "max_score": 26.3458064931194, "measured_at": null, "min_score": 0.0, "model_code_failure_rate": 0.375, "model_code_failures": 3, "model_display_name": "Gemini 3.1 Flash Lite", "model_slug": "google-gemini-3-1-flash-lite", "plugin_success_rate": 0.625, "provider": "Google", "provider_key": "google", "rank": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "ranked", "rated_matches": 890, "rating_method": "sequential_elo", "raw_elo": 1129.858452273603, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 10.069269592939264, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 0, "wins": 85 }, { "admitted_plugins": 7, "attempted_matches": 1126, "capped_draws": 149, "codegen_cost_usd": { "admitted_cell_count": 7, "cell_count": 8, "cost_basis_counts": { "provider_reported": 36 }, "evidence_basis": "Provider-reported", "failed_cell_count": 9, "max": 0.215758025, "mean": 0.16162675, "median": 0.1594081875, "min": 0.098579625, "recorded_attempt_count": 36, "run_count": 16, "total": 2.586028 }, "codegen_evaluated_cells": 16, "conditional_success_score": 38.8658202661972, "contributing_entrants": null, "distinct_rated_opponents": 563, "draws": 430, "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": "2026-07-13T15:25:01Z", "losses": 395, "max_score": 76.96313275824961, "measured_at": null, "min_score": 10.797286233281277, "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": 1094, "rating_method": "sequential_elo", "raw_elo": 1460.6381495389985, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 7, "repaired_rate": 0.4375, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 31.609116148077582, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 4, "wins": 269 }, { "admitted_plugins": 5, "attempted_matches": 922, "capped_draws": 229, "codegen_cost_usd": { "admitted_cell_count": 5, "cell_count": 8, "cost_basis_counts": { "provider_reported": 30 }, "evidence_basis": "Provider-reported", "failed_cell_count": 11, "max": 0.0, "mean": 0.0, "median": 0.0, "min": 0.0, "recorded_attempt_count": 30, "run_count": 16, "total": 0.0 }, "codegen_evaluated_cells": 16, "conditional_success_score": 24.008686649798452, "contributing_entrants": null, "distinct_rated_opponents": 461, "draws": 229, "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": "2026-07-13T14:59:14Z", "losses": 546, "max_score": 25.03744784818577, "measured_at": null, "min_score": 22.97992545141114, "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": 910, "rating_method": "sequential_elo", "raw_elo": 1267.6537729184613, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.125, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 17.950680160249153, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 0, "wins": 135 }, { "admitted_plugins": 4, "attempted_matches": 836, "capped_draws": 126, "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": 18.468588629677875, "contributing_entrants": null, "distinct_rated_opponents": 361, "draws": 139, "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": "2026-07-13T11:16:04Z", "losses": 439, "max_score": 25.41066276207961, "measured_at": null, "min_score": 11.1824442971418, "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": 714, "rating_method": "sequential_elo", "raw_elo": 1222.3930169896764, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": 2, "repaired_rate": 0.25, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "track", "score": 15.530169973491637, "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": null, "unilateral_faults": 122, "wins": 136 }, { "admitted_plugins": 1, "attempted_matches": 181, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 5, "max_score": null, "measured_at": "2026-07-13T11:18:41Z", "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": 175, "rating_method": "sequential_elo", "raw_elo": 2109.1361660112448, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 93.92197991363965, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 170 }, { "admitted_plugins": 1, "attempted_matches": 242, "capped_draws": 20, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 87, "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": 14, "max_score": null, "measured_at": "2026-07-13T11:16:52Z", "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": 174, "rating_method": "sequential_elo", "raw_elo": 1927.175418441868, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 78.86564479729775, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 140 }, { "admitted_plugins": 1, "attempted_matches": 180, "capped_draws": 39, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 87, "draws": 39, "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": "2026-07-13T11:01:25Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Qwen3.7 Max", "model_slug": "qwen-qwen3-7-max", "plugin_success_rate": null, "provider": "Alibaba", "provider_key": "qwen", "rank": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 174, "rating_method": "sequential_elo", "raw_elo": 1711.0366002104788, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 60.989697523320025, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 110 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 32, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 49, "max_score": null, "measured_at": "2026-07-13T11:18:16Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1702.4467227979674, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 60.293433204479186, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 95 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 8, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 51, "max_score": null, "measured_at": "2026-07-13T11:04:37Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1679.8001706810571, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 58.420430590270925, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 117 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 35, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 38, "max_score": null, "measured_at": "2026-07-13T11:02:25Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1665.9230862388683, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 57.2727143594015, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 103 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 26, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 26, "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": 36, "max_score": null, "measured_at": "2026-07-13T11:01:25Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Sonnet 5", "model_slug": "claude-sonnet-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1663.7071745456506, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 57.08944547269302, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 114 }, { "admitted_plugins": 1, "attempted_matches": 180, "capped_draws": 21, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 87, "draws": 21, "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": 56, "max_score": null, "measured_at": "2026-07-13T11:03:52Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 174, "rating_method": "sequential_elo", "raw_elo": 1644.069321033238, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 55.45111097302008, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 97 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 25, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 49, "max_score": null, "measured_at": "2026-07-13T10:57:43Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Nemotron 3 Ultra 550B A55B", "model_slug": "nvidia-nemotron-3-ultra-550b-a55b", "plugin_success_rate": null, "provider": "NVIDIA", "provider_key": "nvidia", "rank": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1636.2835514611418, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 54.82135108626354, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 102 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 57, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 42, "max_score": null, "measured_at": "2026-07-13T10:28:56Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1578.4969194660994, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.04205787490594, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 77 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 89, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 89, "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": 46, "max_score": null, "measured_at": "2026-07-13T10:55:38Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1526.3940735456672, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 45.73284709028545, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 118, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 118, "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": 27, "max_score": null, "measured_at": "2026-07-13T11:00:58Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1515.7592394481949, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.85328396900294, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugins": 3, "attempted_matches": 528, "capped_draws": 100, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 264, "draws": 100, "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": 210, "max_score": null, "measured_at": "2026-07-13T11:14:58Z", "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": 528, "rating_method": "sequential_elo", "raw_elo": 1511.6681093946452, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.51492353136073, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 218 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 43, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 43, "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": 75, "max_score": null, "measured_at": "2026-07-13T10:42:32Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5-Pro", "model_slug": "xiaomi-mimo-v2-5-pro", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1489.682001789536, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 42.69654354980565, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 36, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "draws": 36, "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": 76, "max_score": null, "measured_at": "2026-07-13T10:05:42Z", "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": 177, "rating_method": "sequential_elo", "raw_elo": 1471.8617528733166, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 41.22969923130028, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 65 }, { "admitted_plugins": 4, "attempted_matches": 711, "capped_draws": 86, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 356, "draws": 86, "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": 335, "max_score": null, "measured_at": "2026-07-13T11:13:21Z", "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": 708, "rating_method": "sequential_elo", "raw_elo": 1463.6089955402222, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 40.54710400335003, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 287 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 26, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 26, "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": "2026-07-13T09:52:42Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1434.898909401158, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 38.16566067067517, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 70 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 52, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 52, "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": 74, "max_score": null, "measured_at": "2026-07-13T10:25:36Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1429.6313610449524, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 37.73000354323659, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugins": 3, "attempted_matches": 370, "capped_draws": 82, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 190, "draws": 82, "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": 160, "max_score": null, "measured_at": "2026-07-13T11:15:01Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 366, "rating_method": "sequential_elo", "raw_elo": 1448.8989869373763, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 37.098602648581995, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 31.641683018769097, "unilateral_faults": 4, "wins": 124 }, { "admitted_plugins": 4, "attempted_matches": 552, "capped_draws": 100, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 278, "draws": 100, "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": 242, "max_score": null, "measured_at": "2026-07-13T10:41:40Z", "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": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 541, "rating_method": "sequential_elo", "raw_elo": 1414.4520262624924, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.958989185678846, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 21.337361218395134, "unilateral_faults": 5, "wins": 199 }, { "admitted_plugins": 1, "attempted_matches": 279, "capped_draws": 8, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "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": 106, "max_score": null, "measured_at": "2026-07-13T10:36:10Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 157, "rating_method": "sequential_elo", "raw_elo": 1282.434152108439, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.41066276207961, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 122, "wins": 43 }, { "admitted_plugins": 2, "attempted_matches": 360, "capped_draws": 97, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 180, "draws": 97, "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": 209, "max_score": null, "measured_at": "2026-07-13T14:59:14Z", "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": 356, "rating_method": "sequential_elo", "raw_elo": 1251.1205188144445, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 22.97992545141114, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 33, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 121, "max_score": null, "measured_at": "2026-07-13T10:36:46Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1199.5170400431791, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.698200265719244, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 1, "attempted_matches": 178, "capped_draws": 39, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 39, "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": 118, "max_score": null, "measured_at": "2026-07-13T11:07:07Z", "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": 24, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 175, "rating_method": "sequential_elo", "raw_elo": 1165.1188661834126, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.84621538632902, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 40, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "draws": 40, "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": 125, "max_score": null, "measured_at": "2026-07-13T10:55:07Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Gemini 3.1 Flash Lite", "model_slug": "google-gemini-3-1-flash-lite", "plugin_success_rate": null, "provider": "Google", "provider_key": "google", "rank": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1143.1552701268488, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.03675150081587, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 140, "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": "2026-07-13T03:14:08Z", "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": 162, "rating_method": "sequential_elo", "raw_elo": 1499.0901816144049, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.781317813213978, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 147, "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": "2026-07-13T03:20:13Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1498.7049924286634, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.71302727158694, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 150, "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": "2026-07-13T03:14:14Z", "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": 164, "rating_method": "sequential_elo", "raw_elo": 1492.3988762701977, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.62877706153271, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 142, "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": "2026-07-13T03:09:51Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1489.0269354516097, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.03096260214575, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 147, "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": "2026-07-13T03:20:30Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1487.6089971420777, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 12.76276880459896, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 147, "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": "2026-07-13T10:34:56Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1476.895887324943, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.846471160808935, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 124, "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": 31, "max_score": null, "measured_at": "2026-07-13T10:25:55Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1476.6184623443564, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.797286233281277, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 7 }, { "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": 46, "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": 3, "max_score": null, "measured_at": "2026-07-08T14:06:26Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 69, "rating_method": "sequential_elo", "raw_elo": 1493.0798628212344, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.794214509222783, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 16.01143046671968, "unilateral_faults": 5, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 136, "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": "2026-07-13T03:21:44Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1475.1452511629736, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.536099280916575, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 150, "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": "2026-07-13T03:11:47Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1474.5585295004312, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.465845731109994, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": 13, "max_score": null, "measured_at": "2026-07-13T02:42:15Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT 4.1", "model_slug": "gpt-4-1", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1474.2382944956544, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.392264752412776, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 147, "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": "2026-07-13T03:15:32Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1472.726349126907, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.124210580685428, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 3, "attempted_matches": 488, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 443, "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": 41, "max_score": null, "measured_at": "2026-07-13T10:26:32Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 488, "rating_method": "sequential_elo", "raw_elo": 1469.7970680422186, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.599170646265678, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 151, "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": "2026-07-13T03:48:37Z", "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": 164, "rating_method": "sequential_elo", "raw_elo": 1467.242038434574, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.168698365108394, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 12, "max_score": null, "measured_at": "2026-07-13T03:35:28Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1467.129706579994, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.13197672529834, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 17, "max_score": null, "measured_at": "2026-07-13T03:32:04Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1466.8511591185422, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.082592792115568, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugins": 4, "attempted_matches": 650, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 325, "draws": 585, "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": 57, "max_score": null, "measured_at": "2026-07-13T10:26:17Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 650, "rating_method": "sequential_elo", "raw_elo": 1465.476483309628, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 8.830356337516129, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 150, "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": "2026-07-13T03:30:54Z", "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": 162, "rating_method": "sequential_elo", "raw_elo": 1464.8321092855726, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 8.707672962746242, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 3, "attempted_matches": 487, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 421, "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": 54, "max_score": null, "measured_at": "2026-07-13T10:32:45Z", "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": 487, "rating_method": "sequential_elo", "raw_elo": 1461.1149562623204, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 8.054309065535916, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 2, "attempted_matches": 325, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 163, "draws": 289, "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": 35, "max_score": null, "measured_at": "2026-07-13T04:19:50Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "DeepSeek V4 Flash", "model_slug": "deepseek-deepseek-v4-flash", "plugin_success_rate": null, "provider": "DeepSeek", "provider_key": "deepseek", "rank": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 325, "rating_method": "sequential_elo", "raw_elo": 1454.35494993586, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 6.858648160115894, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 141, "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": 22, "max_score": null, "measured_at": "2026-07-13T04:41:25Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Hy3 Preview", "model_slug": "tencent-hy3-preview", "plugin_success_rate": null, "provider": "Tencent", "provider_key": "tencent", "rank": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1437.778851789159, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 3.928336942357347, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 132, "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": 24, "max_score": null, "measured_at": "2026-07-13T05:22:21Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1415.5264805634315, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 0.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 25, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-03", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-09T08:32:42Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 15, "rating_method": "sequential_elo", "raw_elo": 1534.5522330380682, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 55.20623759020802, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 81.25, "unilateral_faults": 3, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 29, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 17, "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": 2, "max_score": null, "measured_at": "2026-07-13T17:37:51Z", "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": 17, "rating_method": "sequential_elo", "raw_elo": 1520.9383308199456, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 52.545153513088835, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 74.10113019775793, "unilateral_faults": 9, "wins": 4 }, { "admitted_plugins": 2, "attempted_matches": 49, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 32, "draws": 15, "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": "2026-07-13T19:18:02Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 33, "rating_method": "sequential_elo", "raw_elo": 1515.0533936190836, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.021467175110054, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 76.10393346764043, "unilateral_faults": 7, "wins": 11 }, { "admitted_plugins": 3, "attempted_matches": 48, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 32, "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": 4, "max_score": null, "measured_at": "2026-07-13T17:59:25Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 32, "rating_method": "sequential_elo", "raw_elo": 1525.1695248876265, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 45.38475762538517, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 94.9352233375065, "unilateral_faults": 16, "wins": 9 }, { "admitted_plugins": 1, "attempted_matches": 27, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 17, "draws": 5, "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": "2026-07-09T08:02:11Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 17, "rating_method": "sequential_elo", "raw_elo": 1493.3081962704764, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 43.2319281351103, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 74.10113019775793, "unilateral_faults": 3, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 23, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 12, "draws": 6, "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": 3, "max_score": null, "measured_at": "2026-07-13T19:18:02Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 12, "rating_method": "sequential_elo", "raw_elo": 1509.940922087195, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 43.223026423674064, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 94.92504905630727, "unilateral_faults": 4, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 27, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 11, "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": 4, "max_score": null, "measured_at": "2026-07-13T18:48:15Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 11, "rating_method": "sequential_elo", "raw_elo": 1514.2292928833303, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 43.1415761094804, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 100.0, "unilateral_faults": 3, "wins": 5 }, { "admitted_plugins": 1, "attempted_matches": 25, "capped_draws": 3, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 8, "draws": 4, "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": 1, "max_score": null, "measured_at": "2026-07-13T19:18:02Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 8, "rating_method": "sequential_elo", "raw_elo": 1530.8524840939854, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 42.723582427118195, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 100.0, "unilateral_faults": 5, "wins": 3 }, { "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": 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": 7, "max_score": null, "measured_at": "2026-07-10T16:22:35Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 25, "rating_method": "sequential_elo", "raw_elo": 1475.1051868078084, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 42.43356332444173, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 54.30806756909202, "unilateral_faults": 3, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 23, "capped_draws": 3, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 12, "draws": 8, "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": "2026-07-13T17:59:25Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 12, "rating_method": "sequential_elo", "raw_elo": 1504.948568600018, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 41.54026541107848, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 94.92504905630727, "unilateral_faults": 4, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 36, "capped_draws": 4, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 18, "draws": 16, "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": "2026-07-13T15:25:01Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 21, "rating_method": "sequential_elo", "raw_elo": 1465.3321920823437, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 36.835938587376226, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 62.850358177805205, "unilateral_faults": 4, "wins": 1 }, { "admitted_plugins": 3, "attempted_matches": 56, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "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": "GB2-03", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T18:48:15Z", "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": 34, "rating_method": "sequential_elo", "raw_elo": 1499.7508607904936, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 35.93453545842982, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 89.35113295832984, "unilateral_faults": 17, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 25, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 16, "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": 5, "max_score": null, "measured_at": "2026-07-13T14:18:39Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.5", "model_slug": "gpt-5-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 16, "rating_method": "sequential_elo", "raw_elo": 1456.4708771844437, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 29.893935867832372, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 77.5178125181665, "unilateral_faults": 8, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 18, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 6, "draws": 4, "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": 1, "max_score": null, "measured_at": "2026-07-13T18:14:57Z", "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": 6, "rating_method": "sequential_elo", "raw_elo": 1501.8089182415472, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 26.916449137448275, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 100.0, "unilateral_faults": 9, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 12, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 7, "draws": 4, "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": "2026-07-06T04:25:17Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Qwen3.7 Max", "model_slug": "qwen-qwen3-7-max", "plugin_success_rate": null, "provider": "Alibaba", "provider_key": "qwen", "rank": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 7, "rating_method": "sequential_elo", "raw_elo": 1488.270588881205, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.64439063164653, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 100.0, "unilateral_faults": 4, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 15, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 4, "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": 0, "max_score": null, "measured_at": "2026-07-06T04:10:11Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 4, "rating_method": "sequential_elo", "raw_elo": 1519.7751984555318, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.63564509379393, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 100.0, "unilateral_faults": 9, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 16, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 7, "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": 4, "max_score": null, "measured_at": "2026-07-13T18:14:57Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 7, "rating_method": "sequential_elo", "raw_elo": 1475.9979555272569, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 21.507682567414136, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 100.0, "unilateral_faults": 5, "wins": 2 }, { "admitted_plugins": 1, "attempted_matches": 12, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 5, "draws": 4, "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": 1, "max_score": null, "measured_at": "2026-07-13T16:11:38Z", "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": 5, "rating_method": "sequential_elo", "raw_elo": 1482.759212617988, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.412330591049, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 100.0, "unilateral_faults": 3, "wins": 0 }, { "admitted_plugins": 3, "attempted_matches": 67, "capped_draws": 1, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 34, "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": 26, "max_score": null, "measured_at": "2026-07-13T19:18:02Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4 Nano", "model_slug": "gpt-5-4-nano", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 45, "rating_method": "sequential_elo", "raw_elo": 1426.644809610924, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.56210066612941, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 76.96791901759822, "unilateral_faults": 6, "wins": 6 }, { "admitted_plugins": 1, "attempted_matches": 9, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 3, "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": 1, "max_score": null, "measured_at": "2026-07-10T13:33:30Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Sol", "model_slug": "gpt-5-6-sol", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 20, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 3, "rating_method": "sequential_elo", "raw_elo": 1507.1991778484949, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 12.279638610710084, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 100.0, "unilateral_faults": 4, "wins": 1 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 107, "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": "2026-07-13T06:51:02Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1570.6589170900013, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.64527994066829, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 115, "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": "2026-07-13T06:16:10Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Sol", "model_slug": "gpt-5-6-sol", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1542.572370442649, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 29.792415737202536, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 100, "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": "2026-07-13T05:07:18Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1518.7080841668571, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.699554352300087, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 141, "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": "2026-07-13T05:32:34Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1510.7262694584142, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 24.30864455521044, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 124, "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": "2026-07-13T05:16:55Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1507.0146083284037, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.702307848111612, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugins": 4, "attempted_matches": 649, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 325, "draws": 488, "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": 79, "max_score": null, "measured_at": "2026-07-13T10:04:30Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 649, "rating_method": "sequential_elo", "raw_elo": 1506.709721011585, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.621129291107756, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 82 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 135, "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": "2026-07-13T05:21:40Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1500.6347515214338, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 22.587398777192348, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 3, "attempted_matches": 488, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 338, "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": 87, "max_score": null, "measured_at": "2026-07-13T10:00:01Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 488, "rating_method": "sequential_elo", "raw_elo": 1492.9971527865705, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 21.2666937570241, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 63 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 120, "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": 25, "max_score": null, "measured_at": "2026-07-13T04:41:57Z", "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": 163, "rating_method": "sequential_elo", "raw_elo": 1488.5008874765424, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.49799593291555, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 138, "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": "2026-07-13T04:51:47Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Sonnet 5", "model_slug": "claude-sonnet-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1487.9874078589992, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.42590004987722, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugins": 1, "attempted_matches": 163, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 27, "max_score": null, "measured_at": "2026-07-13T04:50:17Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1484.21303296907, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.759644541255607, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "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": 11, "max_score": null, "measured_at": "2026-07-13T10:00:51Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 162, "rating_method": "sequential_elo", "raw_elo": 1483.3666845551031, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.597433493036245, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 125, "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": "2026-07-13T04:45:16Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Gemma 4 31B", "model_slug": "google-gemma-4-31b-it", "plugin_success_rate": null, "provider": "Google", "provider_key": "google", "rank": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1482.0576367562858, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.404817189373603, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "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": 23, "max_score": null, "measured_at": "2026-07-13T04:44:59Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 164, "rating_method": "sequential_elo", "raw_elo": 1479.8246362268771, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.02030343183053, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugins": 2, "attempted_matches": 324, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 162, "draws": 241, "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": 48, "max_score": null, "measured_at": "2026-07-13T09:50:10Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 324, "rating_method": "sequential_elo", "raw_elo": 1477.9429189179004, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.663482749304805, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugins": 1, "attempted_matches": 162, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 81, "draws": 120, "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": 30, "max_score": null, "measured_at": "2026-07-13T04:47:20Z", "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": 162, "rating_method": "sequential_elo", "raw_elo": 1476.7933139751856, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.46552537742257, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 3, "attempted_matches": 487, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 244, "draws": 374, "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": 89, "max_score": null, "measured_at": "2026-07-13T10:00:13Z", "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": 487, "rating_method": "sequential_elo", "raw_elo": 1442.9088090480782, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 12.636240270675255, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugins": 2, "attempted_matches": 324, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 162, "draws": 213, "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": 82, "max_score": null, "measured_at": "2026-07-13T10:40:55Z", "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": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 324, "rating_method": "sequential_elo", "raw_elo": 1437.368264770207, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.676689633106054, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugins": 1, "attempted_matches": 164, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 82, "draws": 121, "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": 32, "max_score": null, "measured_at": "2026-07-13T06:02:29Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 163, "rating_method": "sequential_elo", "raw_elo": 1425.569778103603, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 9.661510668959371, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T11:14:29Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4", "model_slug": "gpt-5-4", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1975.6783507073544, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 82.80492164451171, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 171 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T10:54:01Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Nemotron 3 Ultra 550B A55B", "model_slug": "nvidia-nemotron-3-ultra-550b-a55b", "plugin_success_rate": null, "provider": "NVIDIA", "provider_key": "nvidia", "rank": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1734.1724824403618, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 64.09572011977573, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 137 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": "2026-07-13T10:41:20Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 1701.8562513074885, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 61.59221622927624, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 138 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 72, "max_score": null, "measured_at": "2026-07-13T10:41:24Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1700.3153104058115, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 61.47284118437957, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 120 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 81, "max_score": null, "measured_at": "2026-07-13T10:04:28Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Terra", "model_slug": "gpt-5-6-terra", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1615.8517000992508, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 54.92953555759788, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 111 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 74, "max_score": null, "measured_at": "2026-07-13T10:00:14Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 1614.3851529159326, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 54.81592371456018, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 118 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 101, "max_score": null, "measured_at": "2026-07-13T09:06:32Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1531.4907933302377, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 48.39418626411388, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 91 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 89, "max_score": null, "measured_at": "2026-07-13T08:30:02Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1486.7510206741065, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.92824388846506, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 103 }, { "admitted_plugins": 1, "attempted_matches": 200, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 100, "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": 112, "max_score": null, "measured_at": "2026-07-13T11:00:20Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Nex N2 Pro", "model_slug": "nex-agi-nex-n2-pro", "plugin_success_rate": null, "provider": "Nex AGI", "provider_key": "nex-agi", "rank": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 196, "rating_method": "sequential_elo", "raw_elo": 1479.8540775007548, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 44.416706220785926, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 84 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 112, "max_score": null, "measured_at": "2026-07-13T08:06:26Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1420.491315394543, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.79517533017037, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 80 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 111, "max_score": null, "measured_at": "2026-07-13T08:00:20Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1393.859774395402, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 37.73205830927727, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 81 }, { "admitted_plugins": 4, "attempted_matches": 779, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 391, "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": 466, "max_score": null, "measured_at": "2026-07-13T11:23:19Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 775, "rating_method": "sequential_elo", "raw_elo": 1385.1450491351493, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 37.06693423028597, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 309 }, { "admitted_plugins": 3, "attempted_matches": 577, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 289, "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": 359, "max_score": null, "measured_at": "2026-07-13T11:18:27Z", "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": 577, "rating_method": "sequential_elo", "raw_elo": 1361.9867297938474, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 35.26480634810233, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 218 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 135, "max_score": null, "measured_at": "2026-07-13T08:20:38Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.8", "model_slug": "claude-opus-4-8", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1352.0043481632874, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.48956316868455, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 57 }, { "admitted_plugins": 3, "attempted_matches": 577, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 289, "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": 387, "max_score": null, "measured_at": "2026-07-13T11:17:38Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 577, "rating_method": "sequential_elo", "raw_elo": 1281.2970065683303, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 29.013859720451816, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 190 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 120, "max_score": null, "measured_at": "2026-07-13T09:11:14Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 1279.2681339334554, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.85476638325884, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 72 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 133, "max_score": null, "measured_at": "2026-07-13T09:09:02Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5-Pro", "model_slug": "xiaomi-mimo-v2-5-pro", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1274.6569030680926, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.49753925600006, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 59 }, { "admitted_plugins": 1, "attempted_matches": 193, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": 136, "max_score": null, "measured_at": "2026-07-13T10:08:37Z", "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": 193, "rating_method": "sequential_elo", "raw_elo": 1190.9592234534707, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 22.01932568848559, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 57 }, { "admitted_plugins": 3, "attempted_matches": 401, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 204, "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": 346, "max_score": null, "measured_at": "2026-07-13T11:07:07Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4 Nano", "model_slug": "gpt-5-4-nano", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 396, "rating_method": "sequential_elo", "raw_elo": 1199.8553628618754, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.581453206507906, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 31.641683018769097, "unilateral_faults": 5, "wins": 50 }, { "admitted_plugins": 3, "attempted_matches": 580, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 292, "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": 458, "max_score": null, "measured_at": "2026-07-13T11:18:02Z", "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": 580, "rating_method": "sequential_elo", "raw_elo": 1141.3473588954382, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.177778382565194, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 122 }, { "admitted_plugins": 1, "attempted_matches": 193, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": 160, "max_score": null, "measured_at": "2026-07-13T10:40:11Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 193, "rating_method": "sequential_elo", "raw_elo": 1125.827268341438, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.973622730477505, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 151, "max_score": null, "measured_at": "2026-07-13T10:39:33Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1111.2650370731944, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.839746009246886, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 165, "max_score": null, "measured_at": "2026-07-13T11:01:16Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Gemma 4 31B", "model_slug": "google-gemma-4-31b-it", "plugin_success_rate": null, "provider": "Google", "provider_key": "google", "rank": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 1078.2867553229037, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.28495376492924, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 173, "max_score": null, "measured_at": "2026-07-13T10:55:25Z", "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": 192, "rating_method": "sequential_elo", "raw_elo": 981.3486241901296, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 5.775260340878278, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "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": 183, "max_score": null, "measured_at": "2026-07-13T11:15:40Z", "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": 25, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 192, "rating_method": "sequential_elo", "raw_elo": 906.799250116218, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 0.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": "2026-07-13T11:14:43Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4", "model_slug": "gpt-5-4", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 177, "rating_method": "sequential_elo", "raw_elo": 1842.2348648696632, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 77.53470726652617, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 134 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 34, "max_score": null, "measured_at": "2026-07-13T11:13:38Z", "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": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1822.635273528246, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 75.9025597410182, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 129 }, { "admitted_plugins": 3, "attempted_matches": 529, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 265, "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": 236, "max_score": null, "measured_at": "2026-07-13T11:17:06Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 529, "rating_method": "sequential_elo", "raw_elo": 1581.298875583611, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 55.89406080232581, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 291 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 79, "max_score": null, "measured_at": "2026-07-13T10:28:56Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1580.6556232820392, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 55.8383868718608, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 92 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 72, "max_score": null, "measured_at": "2026-07-13T10:26:28Z", "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": 5, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 177, "rating_method": "sequential_elo", "raw_elo": 1578.273544793543, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 55.64788516644634, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 95 }, { "admitted_plugins": 1, "attempted_matches": 177, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 89, "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": 82, "max_score": null, "measured_at": "2026-07-13T09:50:45Z", "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": 177, "rating_method": "sequential_elo", "raw_elo": 1510.6050308546082, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 50.03703003838767, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 85 }, { "admitted_plugins": 4, "attempted_matches": 555, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 282, "draws": 25, "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": 251, "max_score": null, "measured_at": "2026-07-13T11:13:03Z", "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": 7, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 546, "rating_method": "sequential_elo", "raw_elo": 1519.2247670718857, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 49.07869792911936, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 23.731262264076825, "unilateral_faults": 5, "wins": 270 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 83, "max_score": null, "measured_at": "2026-07-13T10:02:25Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1481.6018960616684, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 47.62517099084877, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 85 }, { "admitted_plugins": 3, "attempted_matches": 530, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 266, "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": 325, "max_score": null, "measured_at": "2026-07-13T11:16:54Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5", "model_slug": "xiaomi-mimo-v2-5", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 530, "rating_method": "sequential_elo", "raw_elo": 1383.0378483153977, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.45721318303368, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 202 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 106, "max_score": null, "measured_at": "2026-07-13T10:52:32Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "MiMo-V2.5-Pro", "model_slug": "xiaomi-mimo-v2-5-pro", "plugin_success_rate": null, "provider": "Xiaomi", "provider_key": "xiaomi", "rank": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1360.7970746059034, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 37.608424464229806, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 70 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 121, "max_score": null, "measured_at": "2026-07-13T10:53:02Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1296.9997288863228, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 32.31855413088292, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 53 }, { "admitted_plugins": 3, "attempted_matches": 369, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 188, "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": 258, "max_score": null, "measured_at": "2026-07-13T11:18:07Z", "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": 364, "rating_method": "sequential_elo", "raw_elo": 1309.7151817493252, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 31.13760253997828, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 31.641683018769097, "unilateral_faults": 5, "wins": 99 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 127, "max_score": null, "measured_at": "2026-07-13T10:58:02Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1224.9666880119312, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 26.3458064931194, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 127, "max_score": null, "measured_at": "2026-07-13T11:18:17Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1215.569918034855, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.566656605763445, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 137, "max_score": null, "measured_at": "2026-07-13T11:18:03Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1104.7826259084304, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.380531331721865, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 149, "max_score": null, "measured_at": "2026-07-13T11:18:54Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 176, "rating_method": "sequential_elo", "raw_elo": 1100.4204044235582, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.018829982550667, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 145, "max_score": null, "measured_at": "2026-07-13T11:17:55Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1098.618308520419, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.86940599714282, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 133, "max_score": null, "measured_at": "2026-07-13T11:14:54Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1091.291875403557, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.261921771004491, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugins": 2, "attempted_matches": 354, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 178, "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": 301, "max_score": null, "measured_at": "2026-07-13T11:18:53Z", "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": 354, "rating_method": "sequential_elo", "raw_elo": 1059.1346381430687, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 12.60253042103812, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 52 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 143, "max_score": null, "measured_at": "2026-07-13T11:15:15Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 1058.1316352827216, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 12.512381512184156, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugins": 1, "attempted_matches": 184, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 92, "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": 152, "max_score": null, "measured_at": "2026-07-13T11:18:45Z", "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": 180, "rating_method": "sequential_elo", "raw_elo": 1055.291266118791, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 12.304567698530732, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugins": 1, "attempted_matches": 176, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 88, "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": 168, "max_score": null, "measured_at": "2026-07-13T11:18:37Z", "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": 176, "rating_method": "sequential_elo", "raw_elo": 907.228743755124, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 0.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 190, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": 42, "max_score": null, "measured_at": "2026-07-13T11:18:28Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 184, "rating_method": "sequential_elo", "raw_elo": 1854.1131973283157, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 76.96313275824961, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 142 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T11:15:11Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Qwen3.7 Max", "model_slug": "qwen-qwen3-7-max", "plugin_success_rate": null, "provider": "Alibaba", "provider_key": "qwen", "rank": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1738.410628244269, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 68.2973627113312, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 136 }, { "admitted_plugins": 3, "attempted_matches": 549, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 275, "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": 198, "max_score": null, "measured_at": "2026-07-13T11:17:00Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 544, "rating_method": "sequential_elo", "raw_elo": 1676.977850413982, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 63.69848733561735, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 346 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T10:57:45Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1663.0094819218623, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 62.65785807563824, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 119 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 72, "max_score": null, "measured_at": "2026-07-13T10:53:18Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 1633.610606743942, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 60.45901759460469, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 110 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 73, "max_score": null, "measured_at": "2026-07-13T11:00:51Z", "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": 6, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1612.886056485539, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 58.90895896876939, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 109 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 80, "max_score": null, "measured_at": "2026-07-13T11:07:36Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 1590.4154432664634, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 57.228306437652854, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 102 }, { "admitted_plugins": 1, "attempted_matches": 183, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T10:28:23Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 183, "rating_method": "sequential_elo", "raw_elo": 1560.8378514115036, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 55.02211698080321, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 105 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 100, "max_score": null, "measured_at": "2026-07-13T09:49:12Z", "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": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1484.2995522204433, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 49.29154302405889, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 82 }, { "admitted_plugins": 1, "attempted_matches": 172, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-07", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-12T07:19:31Z", "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": 10, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 168, "rating_method": "sequential_elo", "raw_elo": 1480.2852917577711, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 48.90152257863875, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 4, "wins": 78 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": "2026-07-13T10:02:47Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1474.3073791390875, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 48.54419488465525, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 78 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 115, "max_score": null, "measured_at": "2026-07-13T09:56:36Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 1379.2405515779446, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 41.433827988649966, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 67 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 128, "max_score": null, "measured_at": "2026-07-13T10:08:42Z", "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": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1355.8473767548942, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.684173980817384, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 54 }, { "admitted_plugins": 3, "attempted_matches": 547, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 276, "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": 381, "max_score": null, "measured_at": "2026-07-13T11:18:55Z", "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": 14, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 547, "rating_method": "sequential_elo", "raw_elo": 1281.9524826632933, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 34.15933294953593, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 166 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 140, "max_score": null, "measured_at": "2026-07-13T11:06:38Z", "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": 15, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1262.3474980912197, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 32.691004448541584, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugins": 2, "attempted_matches": 364, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 184, "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": 261, "max_score": null, "measured_at": "2026-07-13T11:16:36Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 364, "rating_method": "sequential_elo", "raw_elo": 1210.7995576360236, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.83556108545949, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 103 }, { "admitted_plugins": 2, "attempted_matches": 365, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 183, "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": 283, "max_score": null, "measured_at": "2026-07-13T11:14:46Z", "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": 365, "rating_method": "sequential_elo", "raw_elo": 1206.821292633953, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.541022224441036, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 82 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 145, "max_score": null, "measured_at": "2026-07-13T10:56:09Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 1172.978743544452, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 26.00681554513185, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugins": 2, "attempted_matches": 370, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 185, "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": 288, "max_score": null, "measured_at": "2026-07-13T11:23:19Z", "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": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 365, "rating_method": "sequential_elo", "raw_elo": 1159.9779010134412, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.03744784818577, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 77 }, { "admitted_plugins": 3, "attempted_matches": 382, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 195, "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": 335, "max_score": null, "measured_at": "2026-07-13T11:14:49Z", "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": 377, "rating_method": "sequential_elo", "raw_elo": 1153.88555576269, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 22.55210323620892, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 31.641683018769097, "unilateral_faults": 5, "wins": 42 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 161, "max_score": null, "measured_at": "2026-07-13T11:13:55Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.6 Luna", "model_slug": "gpt-5-6-luna", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1021.5883999199752, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.683823968600857, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 160, "max_score": null, "measured_at": "2026-07-13T11:15:38Z", "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": 22, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 1019.0260887892624, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 14.492180124912394, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 170, "max_score": null, "measured_at": "2026-07-13T11:14:45Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Nemotron 3 Ultra 550B A55B", "model_slug": "nvidia-nemotron-3-ultra-550b-a55b", "plugin_success_rate": null, "provider": "NVIDIA", "provider_key": "nvidia", "rank": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 182, "rating_method": "sequential_elo", "raw_elo": 969.4067666197518, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 10.780984592176267, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 182, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 91, "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": 178, "max_score": null, "measured_at": "2026-07-13T11:18:28Z", "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": 182, "rating_method": "sequential_elo", "raw_elo": 825.2631495386737, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 0.0, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 0, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "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": "GB2-08", "generation_policy": { "generation_policy": "quality_generation_policy", "stream_idle_timeout_seconds": null, "streaming_enabled": null, "strict_wall_clock_timeout_seconds": null, "timeout_mode": "provider_route_timeout_guard" }, "generation_timing": { "finish_reason": "unknown_legacy", "first_progress_after_seconds": null, "generation_completed_at": null, "generation_started_at": null, "generation_wall_clock_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": "2026-07-13T11:07:15Z", "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": 1, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1972.1744321291676, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 80.92699793368016, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 168 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 19, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 19, "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": "2026-07-13T11:06:22Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Claude Opus 4.5", "model_slug": "claude-opus-4-5", "plugin_success_rate": null, "provider": "Anthropic", "provider_key": "anthropic", "rank": 2, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1953.4202094748457, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 78.8982296737467, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 154 }, { "admitted_plugins": 3, "attempted_matches": 567, "capped_draws": 138, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 284, "draws": 138, "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": 102, "max_score": null, "measured_at": "2026-07-13T11:04:54Z", "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": 3, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 565, "rating_method": "sequential_elo", "raw_elo": 1736.33042286224, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 55.512559137757854, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 325 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 25, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "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": 52, "max_score": null, "measured_at": "2026-07-13T10:48:42Z", "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": 4, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1722.1576383809518, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 53.99114416916196, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 112 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 52, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "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": 41, "max_score": null, "measured_at": "2026-07-13T09:15:36Z", "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": 188, "rating_method": "sequential_elo", "raw_elo": 1588.1145511719858, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 39.541594289860214, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 95 }, { "admitted_plugins": 4, "attempted_matches": 750, "capped_draws": 402, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 4, "distinct_rated_opponents": 377, "draws": 402, "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": 177, "max_score": null, "measured_at": "2026-07-13T11:16:43Z", "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": 750, "rating_method": "sequential_elo", "raw_elo": 1495.6559371907333, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 29.57626057477822, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 171 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 121, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 121, "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": "2026-07-13T11:05:14Z", "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": 188, "rating_method": "sequential_elo", "raw_elo": 1488.6466607664197, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 28.825303955669103, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 151, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 151, "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": "2026-07-13T10:58:26Z", "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": 8, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1459.1719015817816, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 25.633087743778862, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 138, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 138, "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": "2026-07-13T10:58:04Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.5", "model_slug": "gpt-5-5", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 9, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1435.5146429235408, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 23.084345116795618, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 124, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 124, "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": "2026-07-13T10:56:19Z", "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": 188, "rating_method": "sequential_elo", "raw_elo": 1413.7250064681264, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.753531281042477, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 128, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 128, "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": 43, "max_score": null, "measured_at": "2026-07-13T11:02:14Z", "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": 11, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1412.9108924569598, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.649103435748216, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 145, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "draws": 145, "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": 43, "max_score": null, "measured_at": "2026-07-13T11:07:45Z", "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": 12, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 189, "rating_method": "sequential_elo", "raw_elo": 1409.8911668433243, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 20.348748045283045, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugins": 3, "attempted_matches": 561, "capped_draws": 360, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 282, "draws": 360, "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": 153, "max_score": null, "measured_at": "2026-07-13T11:17:23Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "GPT-5.4 Mini", "model_slug": "gpt-5-4-mini", "plugin_success_rate": null, "provider": "OpenAI", "provider_key": "openai", "rank": 13, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 561, "rating_method": "sequential_elo", "raw_elo": 1402.7777329451228, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 19.565765832701924, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugins": 1, "attempted_matches": 189, "capped_draws": 129, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "draws": 129, "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": "2026-07-13T11:03:10Z", "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": 189, "rating_method": "sequential_elo", "raw_elo": 1395.871357285086, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.83830734885763, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugins": 1, "attempted_matches": 192, "capped_draws": 132, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 96, "draws": 132, "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": 49, "max_score": null, "measured_at": "2026-07-13T11:06:10Z", "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": 189, "rating_method": "sequential_elo", "raw_elo": 1391.8628989274982, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 18.40645136621559, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 127, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 127, "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": "2026-07-13T11:16:21Z", "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": 16, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1380.5556298457757, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 17.163271107680195, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 126, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 126, "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": 47, "max_score": null, "measured_at": "2026-07-13T11:14:14Z", "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": 17, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1377.5527713035483, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.839754605623078, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugins": 1, "attempted_matches": 186, "capped_draws": 129, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 93, "draws": 129, "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": 49, "max_score": null, "measured_at": "2026-07-13T11:15:22Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "Gemma 4 31B", "model_slug": "google-gemma-4-31b-it", "plugin_success_rate": null, "provider": "Google", "provider_key": "google", "rank": 18, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 186, "rating_method": "sequential_elo", "raw_elo": 1372.120747480266, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 16.25452912074359, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugins": 3, "attempted_matches": 400, "capped_draws": 238, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 3, "distinct_rated_opponents": 208, "draws": 238, "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": 131, "max_score": null, "measured_at": "2026-07-13T11:18:54Z", "min_score": null, "model_code_failure_rate": null, "model_code_failures": null, "model_display_name": "DeepSeek V4 Flash", "model_slug": "deepseek-deepseek-v4-flash", "plugin_success_rate": null, "provider": "DeepSeek", "provider_key": "deepseek", "rank": 19, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 394, "rating_method": "sequential_elo", "raw_elo": 1387.6906144268287, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 15.853338267771084, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 21.786315039332067, "unilateral_faults": 6, "wins": 25 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 125, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 94, "draws": 125, "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": 57, "max_score": null, "measured_at": "2026-07-13T10:52:12Z", "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": 188, "rating_method": "sequential_elo", "raw_elo": 1348.3105677082017, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_legacy", "generation_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 13.706029670811375, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugins": 2, "attempted_matches": 375, "capped_draws": 239, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 2, "distinct_rated_opponents": 189, "draws": 239, "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": 132, "max_score": null, "measured_at": "2026-07-13T11:14:55Z", "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": 21, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 375, "rating_method": "sequential_elo", "raw_elo": 1329.1473511389008, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.637295057283298, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugins": 1, "attempted_matches": 190, "capped_draws": 130, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 130, "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": 56, "max_score": null, "measured_at": "2026-07-13T11:04:16Z", "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": 189, "rating_method": "sequential_elo", "raw_elo": 1327.0295869443844, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "code_prompt_version": "unknown_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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.421558133782472, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugins": 1, "attempted_matches": 188, "capped_draws": 118, "codegen_cost_usd": null, "codegen_evaluated_cells": null, "conditional_success_score": null, "contributing_entrants": 1, "distinct_rated_opponents": 95, "draws": 118, "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": 64, "max_score": null, "measured_at": "2026-07-13T11:16:04Z", "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": 23, "rank_movement": null, "rank_movement_baseline_at": null, "ranking_status": "not_applicable", "rated_matches": 188, "rating_method": "sequential_elo", "raw_elo": 1324.8868169932389, "reasoning_level": "None", "reasoning_provenance": { "code_output_mode": "unknown_legacy", "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": { "requested_effort": "none", "source": "public_redacted_snapshot", "track_id": "full_freedom/none" }, "provider_route": "unknown_legacy", "reasoning_bucket": "none", "reasoning_bucket_label": "No requested reasoning", "reasoning_policy_version": "gb2_reasoning_provenance_v1", "requested_reasoning_effort": "none" }, "repaired_admitted": null, "repaired_rate": null, "results_cut_id": "gb2-20260713-37697e440dc9", "row_kind": "game", "score": 11.1824442971418, "score_basis": "relative per-game score", "scoring_policy_version": "entrant_identity_equal_mean_v7", "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8", "track_id": "full_freedom/none", "track_name": "None variants", "uncertainty": 0.0, "unilateral_faults": 0, "wins": 6 } ], "schema_version": 6, "snapshot_id": "20260713_194906", "suite_line_id": "gamebench2", "suite_version": "2-known8" }