{"game_alias":null,"public_release_id":"gb2-20261026-cb69502a12d9","row_kind":"track","rows":[{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-astra:37b988a0e154d378","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":24},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.47583,"mean":0.6505529166666667,"median":0.40659249999999997,"min":0.2072175,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":24},"run_count":24,"token_priced_attempt_count":24,"total":15.613270000000004},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":879,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-6-astra","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":24,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":89.10507177707132,"score":89.10507177707132},"GB2-02":{"attempts":3,"playable":82.96418916904214,"score":82.96418916904214},"GB2-03":{"attempts":3,"playable":89.33935974529317,"score":89.33935974529317},"GB2-04":{"attempts":3,"playable":89.14063875254455,"score":89.14063875254455},"GB2-05":{"attempts":3,"playable":95.42288021642845,"score":95.42288021642845},"GB2-06":{"attempts":3,"playable":86.8694252634245,"score":86.8694252634245},"GB2-07":{"attempts":3,"playable":96.3563864921544,"score":96.3563864921544},"GB2-08":{"attempts":3,"playable":88.71530112056003,"score":88.71530112056003}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:59:42Z","losses":886,"max_score":98.93325735214952,"measured_at":null,"min_score":72.62236899416067,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GPT-6 Astra","model_slug":"gpt-6-astra","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"OpenAI","provider_key":"openai","rank":1,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:15:38Z","ranking_status":"ranked","rated_matches":12264,"rating_method":"bradley_terry_newton","raw_elo":2159.4274533296148,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6-astra","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":89.73915656706482,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":10499},{"admitted_plugins":26,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5-5:655478e878abe238","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":30},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":3.092384,"mean":0.8124949166666666,"median":0.267474,"min":0.094852,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":30},"run_count":27,"token_priced_attempt_count":30,"total":21.736292},"codegen_evaluated_cells":26,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":940,"eligibility_flag":true,"entry_count":26,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"claude-opus-5-5","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":23,"first_pass_rate":0.8846153846153846,"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},"headline_games":{"GB2-01":{"attempts":3,"playable":89.76435656585477,"score":89.76435656585477},"GB2-02":{"attempts":3,"playable":90.66743868817797,"score":90.66743868817797},"GB2-03":{"attempts":3,"playable":80.8167274563028,"score":80.8167274563028},"GB2-04":{"attempts":3,"playable":84.51602833601972,"score":84.51602833601972},"GB2-05":{"attempts":3,"playable":93.29321053571618,"score":93.29321053571618},"GB2-06":{"attempts":3,"playable":89.7708078067045,"score":89.7708078067045},"GB2-07":{"attempts":3,"playable":94.3978209257494,"score":94.3978209257494},"GB2-08":{"attempts":5,"playable":86.91522207483105,"score":86.91522207483105}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":["GB2-08"],"infra_failures_excluded":1,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:54:23Z","losses":1175,"max_score":99.48374593708698,"measured_at":null,"min_score":52.762587763769716,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Claude Opus 5.5","model_slug":"claude-opus-5-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Anthropic","provider_key":"anthropic","rank":2,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:20:59Z","ranking_status":"ranked","rated_matches":13340,"rating_method":"bradley_terry_newton","raw_elo":2154.2594307204727,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-5-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":3,"repaired_rate":0.11538461538461539,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":88.76770154866954,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":11225},{"admitted_plugins":27,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5-1:d8bfa7468f9efb5e","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":27,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":30},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":11.79121,"mean":2.3225539838420417,"median":1.126127596791556,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":20,"boardgame-list-prices-2026-09-08":10},"run_count":27,"token_priced_attempt_count":30,"total":64.31171957781584},"codegen_evaluated_cells":27,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":749,"eligibility_flag":true,"entry_count":27,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"claude-fable-5-1","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":24,"first_pass_rate":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},"headline_games":{"GB2-01":{"attempts":3,"playable":85.09349334712874,"score":85.09349334712874},"GB2-02":{"attempts":3,"playable":89.96597587922939,"score":89.96597587922939},"GB2-03":{"attempts":4,"playable":93.65659197143766,"score":93.65659197143766},"GB2-04":{"attempts":4,"playable":75.59904252153194,"score":75.59904252153194},"GB2-05":{"attempts":3,"playable":91.23667517816655,"score":91.23667517816655},"GB2-06":{"attempts":3,"playable":90.19592678809134,"score":90.19592678809134},"GB2-07":{"attempts":4,"playable":91.97704236624698,"score":91.97704236624698},"GB2-08":{"attempts":3,"playable":91.0756418958665,"score":91.0756418958665}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-05","GB2-06","GB2-08"],"infra_failures_excluded":5,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:06:27Z","losses":1215,"max_score":98.24081452142869,"measured_at":null,"min_score":64.6256422345308,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Claude Fable 5.1","model_slug":"claude-fable-5-1","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Anthropic","provider_key":"anthropic","rank":3,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:21:00Z","ranking_status":"ranked","rated_matches":13784,"rating_method":"bradley_terry_newton","raw_elo":2103.409694308982,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-fable-5-1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":3,"repaired_rate":0.1111111111111111,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":88.60004874346238,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":11820},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-1-sol:59bf9dfe6a652969","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.355686,"mean":0.133143125,"median":0.0768835,"min":0.0400035,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":25},"run_count":24,"token_priced_attempt_count":25,"total":3.1954350000000007},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":890,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-6.1-sol","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":23,"first_pass_rate":0.9583333333333334,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":67.64844394678822,"score":67.64844394678822},"GB2-02":{"attempts":3,"playable":79.80683956559766,"score":79.80683956559766},"GB2-03":{"attempts":3,"playable":93.61112444837455,"score":93.61112444837455},"GB2-04":{"attempts":3,"playable":85.34411766436392,"score":85.34411766436392},"GB2-05":{"attempts":3,"playable":94.69036448273654,"score":94.69036448273654},"GB2-06":{"attempts":3,"playable":87.26876988775354,"score":87.26876988775354},"GB2-07":{"attempts":3,"playable":95.4000297519724,"score":95.4000297519724},"GB2-08":{"attempts":3,"playable":84.00345764701542,"score":84.00345764701542}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:57:23Z","losses":1370,"max_score":98.23172588248056,"measured_at":null,"min_score":51.52882128415899,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GPT-6.1 Sol","model_slug":"gpt-6-1-sol","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"OpenAI","provider_key":"openai","rank":4,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:17:41Z","ranking_status":"ranked","rated_matches":12264,"rating_method":"bradley_terry_newton","raw_elo":2084.580738056049,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6.1-sol","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":1,"repaired_rate":0.041666666666666664,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":85.9716434243253,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":10004},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:gemini-4-argon:7f58079739d57d00","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.582036,"mean":0.20718633333333333,"median":0.09228,"min":0.062404,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":28},"run_count":24,"token_priced_attempt_count":28,"total":4.972472},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":960,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"google","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"gemini-4-argon","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":20,"first_pass_rate":0.8333333333333334,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":92.96786719250883,"score":92.96786719250883},"GB2-02":{"attempts":3,"playable":79.11339082681899,"score":79.11339082681899},"GB2-03":{"attempts":3,"playable":86.026447093223,"score":86.026447093223},"GB2-04":{"attempts":3,"playable":72.13765196143093,"score":72.13765196143093},"GB2-05":{"attempts":3,"playable":91.70839638119408,"score":91.70839638119408},"GB2-06":{"attempts":3,"playable":93.57765180649874,"score":93.57765180649874},"GB2-07":{"attempts":3,"playable":73.86654091603708,"score":73.86654091603708},"GB2-08":{"attempts":3,"playable":76.93286089946498,"score":76.93286089946498}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:57Z","losses":1716,"max_score":97.59621949905328,"measured_at":null,"min_score":59.444836404257536,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Gemini 4 Argon","model_slug":"gemini-4-argon","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Google","provider_key":"google","rank":5,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:07:57Z","ranking_status":"ranked","rated_matches":12265,"rating_method":"bradley_terry_newton","raw_elo":1972.8481427723075,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"gemini-4-argon","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"google","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":4,"repaired_rate":0.16666666666666666,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":83.29135088464709,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":9589},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k3-1-pro:282499765e15824a","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.520818,"mean":0.2783112166666667,"median":0.227979,"min":0.093456,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":24},"recorded_attempt_count":24,"run_count":24,"total":6.679469199999999},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":1181,"eligibility_flag":false,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"moonshotai/kimi-k3.1-pro","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":24,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":65.99690136083493,"score":65.99690136083493},"GB2-02":{"attempts":3,"playable":79.43193483784925,"score":79.43193483784925},"GB2-03":{"attempts":3,"playable":88.27733468525632,"score":88.27733468525632},"GB2-04":{"attempts":3,"playable":81.615561366007,"score":81.615561366007},"GB2-05":{"attempts":3,"playable":85.3448453006314,"score":85.3448453006314},"GB2-06":{"attempts":3,"playable":89.85734070960962,"score":89.85734070960962},"GB2-07":{"attempts":3,"playable":79.89582656411649,"score":79.89582656411649},"GB2-08":{"attempts":3,"playable":92.86147202501836,"score":92.86147202501836}},"ineligibility_reason_codes":["fixed_coverage_incomplete"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:57Z","losses":1571,"max_score":95.55388239609753,"measured_at":null,"min_score":43.485097050144255,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Kimi K3.1 Pro","model_slug":"moonshotai-kimi-k3-1-pro","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Moonshot","provider_key":"moonshotai","rank":6,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"partial","rated_matches":11776,"rating_method":"bradley_terry_newton","raw_elo":1949.2068187182197,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k3.1-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":82.91015210616541,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":9024},{"admitted_plugins":41,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5:c67dec61197bb515","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":41,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":48},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":7,"max":2.09943,"mean":0.703821875,"median":0.48028875,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":48},"run_count":48,"token_priced_attempt_count":48,"total":33.783449999999995},"codegen_evaluated_cells":48,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2690,"eligibility_flag":true,"entry_count":41,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"claude-opus-5","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":41,"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},"headline_games":{"GB2-01":{"attempts":6,"playable":72.79797622160557,"score":72.79797622160557},"GB2-02":{"attempts":6,"playable":74.85751737915977,"score":74.85751737915977},"GB2-03":{"attempts":6,"playable":77.71484544433575,"score":77.71484544433575},"GB2-04":{"attempts":6,"playable":58.10556718072454,"score":58.10556718072454},"GB2-05":{"attempts":6,"playable":90.47948806016366,"score":90.47948806016366},"GB2-06":{"attempts":1,"playable":88.61699922741556,"score":88.61699922741556},"GB2-07":{"attempts":4,"playable":85.39201401487168,"score":85.39201401487168},"GB2-08":{"attempts":6,"playable":81.99248710158273,"score":81.99248710158273}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:53:21Z","losses":3672,"max_score":95.89865809396942,"measured_at":null,"min_score":44.74996282207886,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Claude Opus 5","model_slug":"claude-opus-5","performance_rejected_game_aliases":["GB2-06","GB2-07"],"performance_rejections":7,"plugin_success_rate":null,"provider":"Anthropic","provider_key":"anthropic","rank":7,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:14:15Z","ranking_status":"ranked","rated_matches":20957,"rating_method":"bradley_terry_newton","raw_elo":1897.3938988045488,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":78.1353671853794,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":14595},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-sol:6feebbfece79c4cb","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.225321,"mean":0.10943510416666667,"median":0.0772785,"min":0.033231000000000004,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":25},"run_count":24,"token_priced_attempt_count":25,"total":2.6264425000000005},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":1572,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-6-sol","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":23,"first_pass_rate":0.9583333333333334,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":37.34508605251494,"score":37.34508605251494},"GB2-02":{"attempts":3,"playable":68.67341510548484,"score":68.67341510548484},"GB2-03":{"attempts":3,"playable":83.9238618625356,"score":83.9238618625356},"GB2-04":{"attempts":3,"playable":68.60793756021666,"score":68.60793756021666},"GB2-05":{"attempts":3,"playable":87.74504261374699,"score":87.74504261374699},"GB2-06":{"attempts":3,"playable":81.77693599914004,"score":81.77693599914004},"GB2-07":{"attempts":3,"playable":82.03156085480362,"score":82.03156085480362},"GB2-08":{"attempts":3,"playable":87.13118171285733,"score":87.13118171285733}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:50:40Z","losses":2466,"max_score":94.40710040325735,"measured_at":null,"min_score":10.356509846524498,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GPT-6 Sol","model_slug":"gpt-6-sol","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"OpenAI","provider_key":"openai","rank":8,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:20:38Z","ranking_status":"ranked","rated_matches":12264,"rating_method":"bradley_terry_newton","raw_elo":1861.921500020736,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6-sol","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":1,"repaired_rate":0.041666666666666664,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":74.6543777201625,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":8226},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-sol:2d10b9c97aae0a3b","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.17244375,"mean":0.3844993229166666,"median":0.23243875,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":9.22798375},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":1678,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.6-sol","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":23,"first_pass_rate":0.9583333333333334,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":74.4383451676892,"score":74.4383451676892},"GB2-02":{"attempts":3,"playable":63.1856358272517,"score":63.1856358272517},"GB2-03":{"attempts":3,"playable":65.49737405025711,"score":65.49737405025711},"GB2-04":{"attempts":3,"playable":67.86626132998586,"score":67.86626132998586},"GB2-05":{"attempts":3,"playable":68.76280511643667,"score":68.76280511643667},"GB2-06":{"attempts":3,"playable":62.7995232098101,"score":62.7995232098101},"GB2-07":{"attempts":3,"playable":69.21418690191489,"score":69.21418690191489},"GB2-08":{"attempts":3,"playable":77.98704703244748,"score":77.98704703244748}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:03:22Z","losses":3239,"max_score":88.7341773057466,"measured_at":null,"min_score":41.39310769434979,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GPT-5.6 Sol","model_slug":"gpt-5-6-sol","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"OpenAI","provider_key":"openai","rank":9,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:22:52Z","ranking_status":"ranked","rated_matches":12264,"rating_method":"bradley_terry_newton","raw_elo":1692.1038207110687,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-sol","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":1,"repaired_rate":0.041666666666666664,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":68.71889732947413,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":7347},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5:ad109cd0d8c88daa","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":2.14955,"mean":0.7608541666666667,"median":0.47084000000000004,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":24},"run_count":24,"token_priced_attempt_count":24,"total":18.2605},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":1958,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"claude-fable-5","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":24,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":78.02734128003563,"score":78.02734128003563},"GB2-02":{"attempts":3,"playable":60.51420484516879,"score":60.51420484516879},"GB2-03":{"attempts":3,"playable":47.596672170908796,"score":47.596672170908796},"GB2-04":{"attempts":3,"playable":58.850930683219,"score":58.850930683219},"GB2-05":{"attempts":3,"playable":64.90913079811553,"score":64.90913079811553},"GB2-06":{"attempts":3,"playable":82.11945177061433,"score":82.11945177061433},"GB2-07":{"attempts":3,"playable":67.17881235615329,"score":67.17881235615329},"GB2-08":{"attempts":3,"playable":81.95832162081943,"score":81.95832162081943}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:48:13Z","losses":3184,"max_score":92.97385603080852,"measured_at":null,"min_score":20.85286434586851,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Claude Fable 5","model_slug":"claude-fable-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Anthropic","provider_key":"anthropic","rank":10,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:32:54Z","ranking_status":"ranked","rated_matches":12264,"rating_method":"bradley_terry_newton","raw_elo":1707.1128977443418,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-fable-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":67.64435819062936,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":7122},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-wonder:5ab3b35616053c81","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.680268,"mean":0.2861911833333333,"median":0.206604,"min":0.09556,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":30},"recorded_attempt_count":30,"run_count":24,"total":6.868588399999999},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2250,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-wonder","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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},"headline_games":{"GB2-01":{"attempts":3,"playable":69.12115266528907,"score":69.12115266528907},"GB2-02":{"attempts":3,"playable":55.29575213336481,"score":55.29575213336481},"GB2-03":{"attempts":3,"playable":45.64873763691519,"score":45.64873763691519},"GB2-04":{"attempts":3,"playable":58.436023354009336,"score":58.436023354009336},"GB2-05":{"attempts":3,"playable":87.86645242679431,"score":87.86645242679431},"GB2-06":{"attempts":3,"playable":76.88027256656011,"score":76.88027256656011},"GB2-07":{"attempts":3,"playable":71.87919552199297,"score":71.87919552199297},"GB2-08":{"attempts":3,"playable":65.7553481865781,"score":65.7553481865781}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:50:59Z","losses":3200,"max_score":93.07462175455832,"measured_at":null,"min_score":17.08812627475027,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Muse Wonder","model_slug":"meta-muse-wonder","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Meta","provider_key":"meta","rank":11,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T16:50:59Z","ranking_status":"ranked","rated_matches":12263,"rating_method":"bradley_terry_newton","raw_elo":1704.8881552033795,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-wonder","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":3,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":66.360366811438,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":6813},{"admitted_plugins":23,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3:1bd88701a8bc2787","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.9384062,"mean":0.2535328433333333,"median":0.1720692,"min":0.0217974,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":28,"run_count":24,"total":6.084788240000001},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2102,"eligibility_flag":true,"entry_count":23,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"z-ai/glm-5.3","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01"],"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},"headline_games":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":60.01415966011352,"score":40.009439773409014},"GB2-02":{"attempts":3,"playable":57.38827055721098,"score":57.38827055721098},"GB2-03":{"attempts":3,"playable":68.50875129105536,"score":68.50875129105536},"GB2-04":{"attempts":3,"playable":69.75879863429311,"score":69.75879863429311},"GB2-05":{"attempts":3,"playable":72.35485792778526,"score":72.35485792778526},"GB2-06":{"attempts":3,"playable":77.77405117187433,"score":77.77405117187433},"GB2-07":{"attempts":3,"playable":75.75480727616724,"score":75.75480727616724},"GB2-08":{"attempts":3,"playable":63.812462700785574,"score":63.812462700785574}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:05:10Z","losses":2844,"max_score":92.97385603080852,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.041666666666666664,"model_code_failures":1,"model_display_name":"GLM-5.3","model_slug":"z-ai-glm-5-3","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Zhipu","provider_key":"z-ai","rank":12,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:06:22Z","ranking_status":"ranked","rated_matches":11747,"rating_method":"bradley_terry_newton","raw_elo":1737.1988516182914,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":2,"repaired_rate":0.08333333333333333,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":65.67017991657261,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":6801},{"admitted_plugins":21,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-7:d952d585292a2c76","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":1.2177,"mean":0.4203770833333333,"median":0.380795,"min":0.0533856,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":29},"recorded_attempt_count":29,"run_count":24,"total":10.089049999999999},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":1031,"eligibility_flag":true,"entry_count":21,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"x-ai/grok-4.7","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03","GB2-04","GB2-06"],"first_pass_admitted":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},"headline_games":{"GB2-01":{"attempts":3,"playable":55.64478851395012,"score":55.64478851395012},"GB2-02":{"attempts":3,"playable":74.38105609074306,"score":74.38105609074306},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":80.34837814926223,"score":53.56558543284149},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":67.78420162519383,"score":45.18946775012922},"GB2-05":{"attempts":3,"playable":76.3656192059414,"score":76.3656192059414},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":86.52710957920813,"score":57.684739719472084},"GB2-07":{"attempts":3,"playable":70.07682688622897,"score":70.07682688622897},"GB2-08":{"attempts":3,"playable":87.03944910882228,"score":87.03944910882228}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:55:26Z","losses":2397,"max_score":93.41214839874009,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":3,"model_display_name":"Grok 4.7","model_slug":"x-ai-grok-4-7","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"xAI","provider_key":"x-ai","rank":13,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:17:40Z","ranking_status":"ranked","rated_matches":10770,"rating_method":"bradley_terry_newton","raw_elo":1823.9157160393738,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.7","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":2,"repaired_rate":0.08333333333333333,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":64.99344158851608,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":7342},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-1-flash-1017:11c892b6e18e7c72","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.11170938600000001,"mean":0.0411402025,"median":0.037120068,"min":0.00308565,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":27},"recorded_attempt_count":27,"run_count":24,"total":0.9873648600000001},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2175,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4.1-flash-1017","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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},"headline_games":{"GB2-01":{"attempts":3,"playable":75.47936527617212,"score":75.47936527617212},"GB2-02":{"attempts":3,"playable":56.27206891131873,"score":56.27206891131873},"GB2-03":{"attempts":3,"playable":45.96271504595918,"score":45.96271504595918},"GB2-04":{"attempts":3,"playable":60.67637985206303,"score":60.67637985206303},"GB2-05":{"attempts":3,"playable":62.736626792975215,"score":62.736626792975215},"GB2-06":{"attempts":3,"playable":69.2890949169914,"score":69.2890949169914},"GB2-07":{"attempts":3,"playable":59.91203425761618,"score":59.91203425761618},"GB2-08":{"attempts":3,"playable":77.1333245994046,"score":77.1333245994046}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:50:09Z","losses":3639,"max_score":84.27255262799545,"measured_at":null,"min_score":33.30720043746538,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"DeepSeek V4.1 Flash 1017","model_slug":"deepseek-deepseek-v4-1-flash-1017","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"DeepSeek","provider_key":"deepseek","rank":14,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T17:50:09Z","ranking_status":"ranked","rated_matches":12260,"rating_method":"bradley_terry_newton","raw_elo":1631.5740698222842,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4.1-flash-1017","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":3,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":63.43270120656255,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":6446},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5-5:455c32eab08ae82c","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.72702,"mean":0.21663491666666665,"median":0.058081,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"run_count":24,"token_priced_attempt_count":28,"total":5.199238},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2109,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"claude-sonnet-5-5","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":20,"first_pass_rate":0.8333333333333334,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":59.545403869126524,"score":59.545403869126524},"GB2-02":{"attempts":3,"playable":61.75072730977678,"score":61.75072730977678},"GB2-03":{"attempts":3,"playable":58.63277592898211,"score":58.63277592898211},"GB2-04":{"attempts":3,"playable":56.478012701276356,"score":56.478012701276356},"GB2-05":{"attempts":3,"playable":43.73283861049588,"score":43.73283861049588},"GB2-06":{"attempts":3,"playable":61.60341237032839,"score":61.60341237032839},"GB2-07":{"attempts":3,"playable":70.60018416029764,"score":70.60018416029764},"GB2-08":{"attempts":3,"playable":81.03766466107267,"score":81.03766466107267}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:58Z","losses":3822,"max_score":98.97237080500244,"measured_at":null,"min_score":14.322008174638762,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Claude Sonnet 5.5","model_slug":"claude-sonnet-5-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Anthropic","provider_key":"anthropic","rank":15,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:04:54Z","ranking_status":"ranked","rated_matches":12264,"rating_method":"bradley_terry_newton","raw_elo":1692.0124118521749,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-sonnet-5-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":4,"repaired_rate":0.16666666666666666,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":61.672627451419544,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":6333},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-6:8e3e5018c841df4d","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28029,"mean":0.13107158333333335,"median":0.12371399999999999,"min":0.027072,"recorded_attempt_count":27,"run_count":24,"total":3.1457180000000005},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2989,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"x-ai/grok-4.6","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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},"headline_games":{"GB2-01":{"attempts":3,"playable":59.945710831495376,"score":59.945710831495376},"GB2-02":{"attempts":3,"playable":60.64171007306382,"score":60.64171007306382},"GB2-03":{"attempts":3,"playable":54.642487794993606,"score":54.642487794993606},"GB2-04":{"attempts":3,"playable":56.1651601782638,"score":56.1651601782638},"GB2-05":{"attempts":3,"playable":73.00065410228923,"score":73.00065410228923},"GB2-06":{"attempts":3,"playable":53.25793054650156,"score":53.25793054650156},"GB2-07":{"attempts":3,"playable":70.1081126356943,"score":70.1081126356943},"GB2-08":{"attempts":3,"playable":60.64486082067217,"score":60.64486082067217}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:51:38Z","losses":3526,"max_score":85.00449802467791,"measured_at":null,"min_score":13.704028343787897,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Grok 4.6","model_slug":"x-ai-grok-4-6","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"xAI","provider_key":"x-ai","rank":16,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:17:18Z","ranking_status":"ranked","rated_matches":12263,"rating_method":"bradley_terry_newton","raw_elo":1597.4988888730202,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.6","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":3,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":61.05082837287173,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":5748},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-8-flash:b8343a8c4f242bb9","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2764612177973556,"mean":0.08231859375,"median":0.06440174762499168,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":1.9756462499999998},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2408,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.8-flash","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":23,"first_pass_rate":0.9583333333333334,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":61.071609658113346,"score":61.071609658113346},"GB2-02":{"attempts":3,"playable":50.10874937058625,"score":50.10874937058625},"GB2-03":{"attempts":3,"playable":69.25956906229072,"score":69.25956906229072},"GB2-04":{"attempts":3,"playable":51.32723164139757,"score":51.32723164139757},"GB2-05":{"attempts":3,"playable":59.30442629553894,"score":59.30442629553894},"GB2-06":{"attempts":3,"playable":80.48059755963308,"score":80.48059755963308},"GB2-07":{"attempts":3,"playable":56.65909001065621,"score":56.65909001065621},"GB2-08":{"attempts":3,"playable":59.6036626666056,"score":59.6036626666056}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:47:54Z","losses":3851,"max_score":88.61699922741556,"measured_at":null,"min_score":40.05218343975386,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Gemini 3.8 Flash","model_slug":"google-gemini-3-8-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Google","provider_key":"google","rank":17,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:13:27Z","ranking_status":"ranked","rated_matches":12264,"rating_method":"bradley_terry_newton","raw_elo":1599.7573799317279,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.8-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":1,"repaired_rate":0.041666666666666664,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":60.976867033102714,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":6005},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-3:07660eac5f818c9a","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.358603,"mean":0.10824926041666667,"median":0.050446875,"min":0.017614,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":27,"run_count":24,"total":2.5979822500000007},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2242,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-spark-1.3","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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},"headline_games":{"GB2-01":{"attempts":3,"playable":59.56850786159851,"score":59.56850786159851},"GB2-02":{"attempts":3,"playable":55.99258597942677,"score":55.99258597942677},"GB2-03":{"attempts":3,"playable":67.23438275469339,"score":67.23438275469339},"GB2-04":{"attempts":3,"playable":52.92226867121973,"score":52.92226867121973},"GB2-05":{"attempts":3,"playable":59.961613575740635,"score":59.961613575740635},"GB2-06":{"attempts":3,"playable":69.33502790114143,"score":69.33502790114143},"GB2-07":{"attempts":3,"playable":50.27667758984105,"score":50.27667758984105},"GB2-08":{"attempts":3,"playable":62.49126532755784,"score":62.49126532755784}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:54:38Z","losses":4100,"max_score":84.72703232529484,"measured_at":null,"min_score":26.816405095011675,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Muse Spark 1.3","model_slug":"meta-muse-spark-1-3","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Meta","provider_key":"meta","rank":18,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:02:08Z","ranking_status":"ranked","rated_matches":12264,"rating_method":"bradley_terry_newton","raw_elo":1579.0867134154755,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-spark-1.3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":2,"repaired_rate":0.08333333333333333,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":59.72279120765243,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":5922},{"admitted_plugins":23,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-open:49b386635d2620f4","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.15589245,"mean":0.05806762291666667,"median":0.032108575,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":26},"recorded_attempt_count":27,"run_count":24,"total":1.3936229500000001},"codegen_evaluated_cells":23,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2129,"eligibility_flag":false,"entry_count":23,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-spark-open","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":20,"first_pass_rate":0.8695652173913043,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":69.59116526057646,"score":69.59116526057646},"GB2-02":{"attempts":2,"playable":44.97685382422647,"score":44.97685382422647},"GB2-03":{"attempts":3,"playable":52.832539963614614,"score":52.832539963614614},"GB2-04":{"attempts":3,"playable":44.48230166257378,"score":44.48230166257378},"GB2-05":{"attempts":3,"playable":52.1826652760445,"score":52.1826652760445},"GB2-06":{"attempts":3,"playable":63.03599264094472,"score":63.03599264094472},"GB2-07":{"attempts":3,"playable":54.818925847519154,"score":54.818925847519154},"GB2-08":{"attempts":3,"playable":78.25760289976516,"score":78.25760289976516}},"ineligibility_reason_codes":["generation_incomplete"],"infra_excluded_game_aliases":["GB2-02"],"infra_failures_excluded":1,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:49:55Z","losses":4120,"max_score":92.30699442734611,"measured_at":null,"min_score":32.73183651180149,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Muse Spark Open","model_slug":"meta-muse-spark-open","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Meta","provider_key":"meta","rank":19,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"partial","rated_matches":11782,"rating_method":"bradley_terry_newton","raw_elo":1584.7478932694137,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-spark-open","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":3,"repaired_rate":0.13043478260869565,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":58.29964782102038,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":5533},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-5:16749021a47b42c6","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07082726666666667,"median":0.0661398,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":34},"recorded_attempt_count":34,"run_count":24,"total":1.6998543999999998},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2561,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"x-ai/grok-4.5","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":20,"first_pass_rate":0.8333333333333334,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":73.32550975897233,"score":73.32550975897233},"GB2-02":{"attempts":3,"playable":51.85956656434964,"score":51.85956656434964},"GB2-03":{"attempts":3,"playable":39.1401135347381,"score":39.1401135347381},"GB2-04":{"attempts":3,"playable":43.332986106347384,"score":43.332986106347384},"GB2-05":{"attempts":3,"playable":61.2955042190537,"score":61.2955042190537},"GB2-06":{"attempts":3,"playable":47.60965884887411,"score":47.60965884887411},"GB2-07":{"attempts":3,"playable":61.494631657523314,"score":61.494631657523314},"GB2-08":{"attempts":3,"playable":87.97511658962145,"score":87.97511658962145}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:18:06Z","losses":4056,"max_score":90.53996071061802,"measured_at":null,"min_score":15.752084763952883,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Grok 4.5","model_slug":"x-ai-grok-4-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"xAI","provider_key":"x-ai","rank":20,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:06:41Z","ranking_status":"ranked","rated_matches":12263,"rating_method":"bradley_terry_newton","raw_elo":1580.923264233469,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":4,"repaired_rate":0.16666666666666666,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":58.254135909935,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":5646},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flashx:d01e9c0cb656f07b","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.09557687,"mean":0.03177873833333334,"median":0.025158225,"min":0.00543595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":29},"recorded_attempt_count":29,"run_count":24,"total":0.7626897200000001},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2603,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"z-ai/glm-5.3-flashx","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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},"headline_games":{"GB2-01":{"attempts":3,"playable":61.82023570125329,"score":61.82023570125329},"GB2-02":{"attempts":3,"playable":54.47284991410866,"score":54.47284991410866},"GB2-03":{"attempts":3,"playable":63.33512100666218,"score":63.33512100666218},"GB2-04":{"attempts":3,"playable":62.00393183817469,"score":62.00393183817469},"GB2-05":{"attempts":3,"playable":56.34900698086208,"score":56.34900698086208},"GB2-06":{"attempts":3,"playable":67.20437084313345,"score":67.20437084313345},"GB2-07":{"attempts":3,"playable":66.05609167262041,"score":66.05609167262041},"GB2-08":{"attempts":3,"playable":29.5987148539283,"score":29.5987148539283}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:25Z","losses":4185,"max_score":84.85546915992354,"measured_at":null,"min_score":19.026733063599135,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GLM-5.3 FlashX","model_slug":"z-ai-glm-5-3-flashx","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Zhipu","provider_key":"z-ai","rank":21,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:12:16Z","ranking_status":"ranked","rated_matches":12264,"rating_method":"bradley_terry_newton","raw_elo":1544.5256981557234,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3-flashx","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":5,"repaired_rate":0.20833333333333334,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":57.60504035134287,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":5476},{"admitted_plugins":23,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:claude-haiku-5-5:455a86fa0ec4fe60","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0653315,"mean":0.020964483333333336,"median":0.012623549999999999,"min":0.0020421000000000003,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":28},"run_count":24,"token_priced_attempt_count":28,"total":0.5031476},"codegen_evaluated_cells":23,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2618,"eligibility_flag":false,"entry_count":23,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"claude-haiku-5-5","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":22,"first_pass_rate":0.9565217391304348,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":40.81592221955691,"score":40.81592221955691},"GB2-02":{"attempts":3,"playable":58.61208442610843,"score":58.61208442610843},"GB2-03":{"attempts":2,"playable":55.45062198753941,"score":55.45062198753941},"GB2-04":{"attempts":3,"playable":63.135820902353565,"score":63.135820902353565},"GB2-05":{"attempts":3,"playable":53.38848570569018,"score":53.38848570569018},"GB2-06":{"attempts":3,"playable":70.02989645121926,"score":70.02989645121926},"GB2-07":{"attempts":3,"playable":58.678591756396,"score":58.678591756396},"GB2-08":{"attempts":3,"playable":51.57418401844583,"score":51.57418401844583}},"ineligibility_reason_codes":["generation_incomplete"],"infra_excluded_game_aliases":["GB2-03"],"infra_failures_excluded":1,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:28:13Z","losses":4069,"max_score":91.83900036619863,"measured_at":null,"min_score":16.24037589149305,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Claude Haiku 5.5","model_slug":"claude-haiku-5-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Anthropic","provider_key":"anthropic","rank":22,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"partial","rated_matches":11770,"rating_method":"bradley_terry_newton","raw_elo":1556.3906101147531,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-haiku-5-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":1,"repaired_rate":0.043478260869565216,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":57.26920075540992,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":5083},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flash:bf561de6bfd6a4fd","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02871725,"mean":0.008139411458333334,"median":0.005035225,"min":0.001111625,"recorded_attempt_count":28,"run_count":24,"total":0.195345875},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2169,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"z-ai/glm-5.3-flash","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":20,"first_pass_rate":0.8333333333333334,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":58.116106176436375,"score":58.116106176436375},"GB2-02":{"attempts":3,"playable":52.581739533246896,"score":52.581739533246896},"GB2-03":{"attempts":3,"playable":71.74503189743697,"score":71.74503189743697},"GB2-04":{"attempts":3,"playable":72.46521015506944,"score":72.46521015506944},"GB2-05":{"attempts":3,"playable":53.47620686150221,"score":53.47620686150221},"GB2-06":{"attempts":3,"playable":47.51896278648835,"score":47.51896278648835},"GB2-07":{"attempts":3,"playable":72.39619581433568,"score":72.39619581433568},"GB2-08":{"attempts":3,"playable":26.675525700274658,"score":26.675525700274658}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:37:36Z","losses":4478,"max_score":81.45735359322124,"measured_at":null,"min_score":17.24808744063479,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GLM-5.3 Flash","model_slug":"z-ai-glm-5-3-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Zhipu","provider_key":"z-ai","rank":23,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:18:28Z","ranking_status":"ranked","rated_matches":12263,"rating_method":"bradley_terry_newton","raw_elo":1521.9397273620498,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":4,"repaired_rate":0.16666666666666666,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":56.87187236559882,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":5616},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max-0902:8a79f157db205041","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.518502,"mean":0.20968833333333334,"median":0.124697,"min":0.054514,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":19,"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":30,"run_count":24,"total":5.03252},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":3001,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.8-max-0902","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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},"headline_games":{"GB2-01":{"attempts":3,"playable":48.37634039151422,"score":48.37634039151422},"GB2-02":{"attempts":3,"playable":46.84228892261627,"score":46.84228892261627},"GB2-03":{"attempts":3,"playable":61.38604365750964,"score":61.38604365750964},"GB2-04":{"attempts":3,"playable":56.13434881666783,"score":56.13434881666783},"GB2-05":{"attempts":3,"playable":65.33300897941776,"score":65.33300897941776},"GB2-06":{"attempts":3,"playable":68.39526626644407,"score":68.39526626644407},"GB2-07":{"attempts":3,"playable":50.76114605467618,"score":50.76114605467618},"GB2-08":{"attempts":3,"playable":45.34812447362585,"score":45.34812447362585}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:49Z","losses":4264,"max_score":92.40236120027856,"measured_at":null,"min_score":26.31601551085625,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Qwen3.8 Max 0902","model_slug":"qwen-qwen3-8-max-0902","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Alibaba","provider_key":"qwen","rank":24,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:04:31Z","ranking_status":"ranked","rated_matches":12264,"rating_method":"bradley_terry_newton","raw_elo":1536.7606682841426,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-max-0902","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":5,"repaired_rate":0.20833333333333334,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":55.32207094530897,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":4999},{"admitted_plugins":23,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4:9608b8753702fb91","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.2530275,"mean":0.6328307291666667,"median":0.26543625,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":27},"run_count":24,"token_priced_attempt_count":27,"total":15.1879375},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2491,"eligibility_flag":true,"entry_count":23,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.4","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02"],"first_pass_admitted":21,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":91.13368962862563,"score":91.13368962862563},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":43.11479577593353,"score":28.743197183955687},"GB2-03":{"attempts":3,"playable":40.3506487529719,"score":40.3506487529719},"GB2-04":{"attempts":3,"playable":43.11141213977535,"score":43.11141213977535},"GB2-05":{"attempts":3,"playable":73.08699157140634,"score":73.08699157140634},"GB2-06":{"attempts":3,"playable":73.95034038677376,"score":73.95034038677376},"GB2-07":{"attempts":3,"playable":46.82589519449482,"score":46.82589519449482},"GB2-08":{"attempts":3,"playable":44.66762424216294,"score":44.66762424216294}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:17Z","losses":3978,"max_score":97.50040588860446,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.041666666666666664,"model_code_failures":1,"model_display_name":"GPT-5.4","model_slug":"gpt-5-4","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"OpenAI","provider_key":"openai","rank":25,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:04:27Z","ranking_status":"ranked","rated_matches":11784,"rating_method":"bradley_terry_newton","raw_elo":1609.0059093367938,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":2,"repaired_rate":0.08333333333333333,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":55.2337248875208,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":5315},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-2-4t-a95b:27c4ceead9a6b15f","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":27},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.22795366666666664,"median":0.16679960729572763,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":27},"run_count":24,"token_priced_attempt_count":27,"total":5.470888},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":3053,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.8-2.4t-a95b","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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},"headline_games":{"GB2-01":{"attempts":3,"playable":49.43483652738795,"score":49.43483652738795},"GB2-02":{"attempts":3,"playable":48.87117735906679,"score":48.87117735906679},"GB2-03":{"attempts":3,"playable":58.56663015581648,"score":58.56663015581648},"GB2-04":{"attempts":3,"playable":43.802824876162724,"score":43.802824876162724},"GB2-05":{"attempts":3,"playable":51.67542135380611,"score":51.67542135380611},"GB2-06":{"attempts":3,"playable":63.21345403070339,"score":63.21345403070339},"GB2-07":{"attempts":3,"playable":48.595474022350686,"score":48.595474022350686},"GB2-08":{"attempts":3,"playable":72.42460426990085,"score":72.42460426990085}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:55:09Z","losses":4305,"max_score":90.05138542578382,"measured_at":null,"min_score":32.155628167045116,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Qwen3.8 2.4T A95B","model_slug":"qwen-qwen3-8-2-4t-a95b","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Alibaba","provider_key":"qwen","rank":26,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:05:18Z","ranking_status":"ranked","rated_matches":12264,"rating_method":"bradley_terry_newton","raw_elo":1532.356697742057,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-2.4t-a95b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":3,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":54.573052824399376,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":4906},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-1-flash:0a96bef3bb84fe9d","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.031583268,"mean":0.0163638035,"median":0.017740284000000002,"min":0.00220635,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":26},"recorded_attempt_count":26,"run_count":24,"total":0.3927312839999999},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":3175,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4.1-flash","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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},"headline_games":{"GB2-01":{"attempts":3,"playable":59.148438368069236,"score":59.148438368069236},"GB2-02":{"attempts":3,"playable":52.51122611991057,"score":52.51122611991057},"GB2-03":{"attempts":3,"playable":54.54687443341282,"score":54.54687443341282},"GB2-04":{"attempts":3,"playable":50.87516661732659,"score":50.87516661732659},"GB2-05":{"attempts":3,"playable":55.58974300772159,"score":55.58974300772159},"GB2-06":{"attempts":3,"playable":62.60778903581805,"score":62.60778903581805},"GB2-07":{"attempts":3,"playable":56.976717857389524,"score":56.976717857389524},"GB2-08":{"attempts":3,"playable":37.44582268641985,"score":37.44582268641985}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:43Z","losses":4369,"max_score":82.56812866647837,"measured_at":null,"min_score":24.29347129725537,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"DeepSeek V4.1 Flash","model_slug":"deepseek-deepseek-v4-1-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"DeepSeek","provider_key":"deepseek","rank":27,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:20:59Z","ranking_status":"ranked","rated_matches":12263,"rating_method":"bradley_terry_newton","raw_elo":1502.9767493049499,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4.1-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":2,"repaired_rate":0.08333333333333333,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":53.71272226575852,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":4719},{"admitted_plugins":23,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-2:7070428b78df5af4","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.2224195,"mean":0.071446625,"median":0.04824225,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":18,"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":27,"run_count":24,"total":1.7147189999999999},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2409,"eligibility_flag":true,"entry_count":23,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-spark-1.2","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":22,"first_pass_rate":0.9565217391304348,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":67.88527572944297,"score":67.88527572944297},"GB2-02":{"attempts":3,"playable":45.72116971349883,"score":45.72116971349883},"GB2-03":{"attempts":3,"playable":53.21313346646502,"score":53.21313346646502},"GB2-04":{"attempts":3,"playable":47.74243731992615,"score":47.74243731992615},"GB2-05":{"attempts":3,"playable":54.361891615453,"score":54.361891615453},"GB2-06":{"attempts":2,"playable":23.408619728961654,"score":23.408619728961654},"GB2-07":{"attempts":3,"playable":57.89475401346008,"score":57.89475401346008},"GB2-08":{"attempts":3,"playable":67.12583456072983,"score":67.12583456072983}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:49Z","losses":4520,"max_score":85.82938002593471,"measured_at":null,"min_score":19.740941347498214,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Muse Spark 1.2","model_slug":"meta-muse-spark-1-2","performance_rejected_game_aliases":["GB2-06"],"performance_rejections":1,"plugin_success_rate":null,"provider":"Meta","provider_key":"meta","rank":28,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T18:36:08Z","ranking_status":"ranked","rated_matches":11762,"rating_method":"bradley_terry_newton","raw_elo":1533.9089413782517,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-spark-1.2","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":1,"repaired_rate":0.043478260869565216,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":53.66606728971573,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":4833},{"admitted_plugins":23,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy4-preview:f4440149415afa63","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.09097980808333334,"median":0.1119999555,"min":0.009391185,"recorded_attempt_count":28,"run_count":24,"total":2.1835153939999996},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2640,"eligibility_flag":true,"entry_count":23,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"tencent/hy4-preview","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02"],"first_pass_admitted":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},"headline_games":{"GB2-01":{"attempts":3,"playable":51.45796696411949,"score":51.45796696411949},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":60.97197592066588,"score":40.64798394711058},"GB2-03":{"attempts":3,"playable":59.04453884432379,"score":59.04453884432379},"GB2-04":{"attempts":3,"playable":44.446796643258416,"score":44.446796643258416},"GB2-05":{"attempts":3,"playable":57.75235880154906,"score":57.75235880154906},"GB2-06":{"attempts":3,"playable":60.254600854956,"score":60.254600854956},"GB2-07":{"attempts":3,"playable":60.895110102345484,"score":60.895110102345484},"GB2-08":{"attempts":3,"playable":51.595340660427986,"score":51.595340660427986}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:44Z","losses":4179,"max_score":89.23574981546986,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.041666666666666664,"model_code_failures":1,"model_display_name":"Hy4 Preview","model_slug":"tencent-hy4-preview","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Tencent","provider_key":"tencent","rank":29,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:06:54Z","ranking_status":"ranked","rated_matches":11784,"rating_method":"bradley_terry_newton","raw_elo":1528.3622176946421,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"tencent","provider_model":"tencent/hy4-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":3,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":53.26183710226135,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":4965},{"admitted_plugins":46,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-6-flash:0d9c66a7efaa96af","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":46,"cell_count":24,"cost_basis_counts":{"provider_reported":130},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.531673125,"mean":0.24710551171874998,"median":0.24728879999999998,"min":0.0411735,"recorded_attempt_count":130,"run_count":52,"total":13.077675974999998},"codegen_evaluated_cells":48,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":5149,"eligibility_flag":true,"entry_count":46,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.6-flash","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-08"],"first_pass_admitted":38,"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},"headline_games":{"GB2-01":{"attempts":6,"playable":53.22947120280666,"score":53.22947120280666},"GB2-02":{"attempts":6,"failed_attempts":1,"playable":44.2674916189132,"score":38.01669357287391},"GB2-03":{"attempts":6,"playable":58.30222758111196,"score":58.30222758111196},"GB2-04":{"attempts":6,"playable":48.922383298974495,"score":48.922383298974495},"GB2-05":{"attempts":6,"playable":67.13980293728622,"score":67.13980293728622},"GB2-06":{"attempts":6,"playable":63.41658403111146,"score":63.41658403111146},"GB2-07":{"attempts":6,"playable":49.13477581545826,"score":49.13477581545826},"GB2-08":{"attempts":6,"failed_attempts":1,"playable":53.62204145996665,"score":41.74511474882007}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":["GB2-02","GB2-03","GB2-07"],"infra_failures_excluded":5,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:27Z","losses":8559,"max_score":83.85508646801725,"measured_at":null,"min_score":18.752394138117857,"model_code_failure_rate":0.041666666666666664,"model_code_failures":2,"model_display_name":"Gemini 3.6 Flash","model_slug":"google-gemini-3-6-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Google","provider_key":"google","rank":30,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:15:38Z","ranking_status":"ranked","rated_matches":23511,"rating_method":"bradley_terry_newton","raw_elo":1539.059817180669,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.6-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":8,"repaired_rate":0.16666666666666666,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":52.48838164855539,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":9803},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:fireworks-ember-1:821e38656eecb7ec","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.508434,"mean":0.171409,"median":0.146631,"min":0.054066,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"recorded_attempt_count":28,"run_count":24,"total":4.113816},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2989,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"fireworks/ember-1","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":20,"first_pass_rate":0.8333333333333334,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":59.68780144994155,"score":59.68780144994155},"GB2-02":{"attempts":3,"playable":44.388756334693575,"score":44.388756334693575},"GB2-03":{"attempts":3,"playable":60.03308572453606,"score":60.03308572453606},"GB2-04":{"attempts":3,"playable":45.11562851619331,"score":45.11562851619331},"GB2-05":{"attempts":3,"playable":44.21785279783825,"score":44.21785279783825},"GB2-06":{"attempts":3,"playable":52.35744341819355,"score":52.35744341819355},"GB2-07":{"attempts":3,"playable":59.00334571957314,"score":59.00334571957314},"GB2-08":{"attempts":3,"playable":54.30589706329817,"score":54.30589706329817}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:06:27Z","losses":4618,"max_score":87.59950869232675,"measured_at":null,"min_score":19.523694017823157,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Ember-1","model_slug":"fireworks-ember-1","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Fireworks AI","provider_key":"fireworks","rank":31,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:21:04Z","ranking_status":"ranked","rated_matches":12264,"rating_method":"bradley_terry_newton","raw_elo":1487.8562012048458,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"fireworks","provider_model":"fireworks/ember-1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":4,"repaired_rate":0.16666666666666666,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":52.388726378033454,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":4657},{"admitted_plugins":79,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:stealth-ox-alpha:bcf866c226eb9ef2","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":79,"cell_count":24,"cost_basis_counts":{"provider_reported":112},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":112,"run_count":88,"total":0.0},"codegen_evaluated_cells":85,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":8251,"eligibility_flag":true,"entry_count":79,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"stealth/ox-alpha","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-03","GB2-08"],"first_pass_admitted":62,"first_pass_rate":0.7380952380952381,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":9,"failed_attempts":1,"playable":54.48051454195302,"score":47.55602714764904},"GB2-02":{"attempts":8,"playable":55.7605382835805,"score":55.7605382835805},"GB2-03":{"attempts":23,"failed_attempts":3,"playable":58.05639394722551,"score":52.10729996334184},"GB2-04":{"attempts":9,"playable":59.45397589319106,"score":59.45397589319106},"GB2-05":{"attempts":9,"playable":54.55134879725673,"score":54.55134879725673},"GB2-06":{"attempts":8,"playable":46.51228991006703,"score":46.51228991006703},"GB2-07":{"attempts":9,"playable":50.68573409502079,"score":50.68573409502079},"GB2-08":{"attempts":9,"failed_attempts":1,"playable":55.05801707098516,"score":51.69719227659158}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":["GB2-02","GB2-03"],"infra_failures_excluded":5,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:13Z","losses":15097,"max_score":74.06155524082445,"measured_at":null,"min_score":20.16494876636143,"model_code_failure_rate":0.05952380952380952,"model_code_failures":5,"model_display_name":"Ox Alpha","model_slug":"stealth-ox-alpha","performance_rejected_game_aliases":["GB2-06"],"performance_rejections":1,"plugin_success_rate":null,"provider":"Other","provider_key":"other","rank":32,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:18:13Z","ranking_status":"ranked","rated_matches":40187,"rating_method":"bradley_terry_newton","raw_elo":1494.2441170996658,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"stealth/ox-alpha","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":17,"repaired_rate":0.20238095238095238,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":52.290550795837326,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":16839},{"admitted_plugins":22,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-8:5f504bf8d13cd087","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":25},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":1.38945,"mean":0.43567666666666666,"median":0.20305499999999999,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":25},"run_count":24,"token_priced_attempt_count":25,"total":10.456240000000001},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2495,"eligibility_flag":true,"entry_count":22,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"claude-opus-4-8","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03"],"first_pass_admitted":21,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":55.53585330792611,"score":55.53585330792611},"GB2-02":{"attempts":3,"playable":53.59917885207099,"score":53.59917885207099},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":31.204237061055146,"score":10.401412353685048},"GB2-04":{"attempts":3,"playable":51.738146668414174,"score":51.738146668414174},"GB2-05":{"attempts":3,"playable":40.0324741750251,"score":40.0324741750251},"GB2-06":{"attempts":3,"playable":70.34614857644128,"score":70.34614857644128},"GB2-07":{"attempts":3,"playable":65.73529110751599,"score":65.73529110751599},"GB2-08":{"attempts":3,"playable":65.55547829022743,"score":65.55547829022743}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-04","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":6,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:18Z","losses":3891,"max_score":83.06751737534383,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.08333333333333333,"model_code_failures":2,"model_display_name":"Claude Opus 4.8","model_slug":"claude-opus-4-8","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Anthropic","provider_key":"anthropic","rank":33,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:04:49Z","ranking_status":"ranked","rated_matches":11275,"rating_method":"bradley_terry_newton","raw_elo":1566.9747243276195,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-4-8","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":1,"repaired_rate":0.041666666666666664,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":51.617997916413266,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":4889},{"admitted_plugins":30,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash:ae38f82fed4234a4","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":30,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":32,"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Combined: Provider-reported + Standard list-price estimate","failed_cell_count":2,"max":0.5094276945411561,"mean":0.1819473937669366,"median":0.18692147314407714,"min":0.043710665151447045,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":32},"recorded_attempt_count":14,"run_count":32,"token_priced_attempt_count":32,"total":4.9824165},"codegen_evaluated_cells":32,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":3138,"eligibility_flag":true,"entry_count":30,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.5-flash","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":22,"first_pass_rate":0.6875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":4,"playable":71.11213512710803,"score":71.11213512710803},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":49.02590731481388,"score":42.42123405192025},"GB2-03":{"attempts":4,"failed_attempts":1,"playable":54.73535610166027,"score":50.89321777915992},"GB2-04":{"attempts":4,"playable":45.38246694915117,"score":45.38246694915117},"GB2-05":{"attempts":4,"playable":45.117778352907806,"score":45.117778352907806},"GB2-06":{"attempts":4,"playable":63.145123774759575,"score":63.145123774759575},"GB2-07":{"attempts":4,"playable":50.50312401702641,"score":50.50312401702641},"GB2-08":{"attempts":4,"playable":40.292919456946116,"score":40.292919456946116}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:55:21Z","losses":6570,"max_score":90.48531473976723,"measured_at":null,"min_score":11.526414967501074,"model_code_failure_rate":0.0625,"model_code_failures":2,"model_display_name":"Gemini 3.5 Flash","model_slug":"google-gemini-3-5-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Google","provider_key":"google","rank":34,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:15:48Z","ranking_status":"ranked","rated_matches":15377,"rating_method":"bradley_terry_newton","raw_elo":1484.3307806849784,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.5-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":8,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":51.10849993862242,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":5669},{"admitted_plugins":22,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-5:9d14cd9c426a28cb","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":26},"cost_is_complete":false,"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-2026-10-09":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":97,"draws":3155,"eligibility_flag":true,"entry_count":22,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.5","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-06"],"first_pass_admitted":21,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":65.70179578073153,"score":65.70179578073153},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":48.88778117281322,"score":32.59185411520881},"GB2-03":{"attempts":3,"playable":43.17566151443841,"score":43.17566151443841},"GB2-04":{"attempts":3,"playable":39.31131441995884,"score":39.31131441995884},"GB2-05":{"attempts":3,"playable":68.8035962844332,"score":68.8035962844332},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":55.45313616439678,"score":36.968757442931185},"GB2-07":{"attempts":3,"playable":62.04487131523927,"score":62.04487131523927},"GB2-08":{"attempts":3,"playable":57.32207148707306,"score":57.32207148707306}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:51:19Z","losses":3682,"max_score":87.00914453270325,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.08333333333333333,"model_code_failures":2,"model_display_name":"GPT-5.5","model_slug":"gpt-5-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"OpenAI","provider_key":"openai","rank":35,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:49:01Z","ranking_status":"ranked","rated_matches":11282,"rating_method":"bradley_terry_newton","raw_elo":1549.0649258654782,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":1,"repaired_rate":0.041666666666666664,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":50.73999029500178,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":4445},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max:28f20064a86160e5","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.40721066666666667,"mean":0.19033848611111112,"median":0.13741799999999998,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":30},"recorded_attempt_count":30,"run_count":29,"total":6.452750000000001},"codegen_evaluated_cells":26,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":3042,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.8-max","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02"],"first_pass_admitted":24,"first_pass_rate":0.96,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":33.939977751428835,"score":33.939977751428835},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":45.079193043121215,"score":36.43737879826312},"GB2-03":{"attempts":3,"playable":51.030697618296664,"score":51.030697618296664},"GB2-04":{"attempts":3,"playable":48.72015787073858,"score":48.72015787073858},"GB2-05":{"attempts":3,"playable":68.70373295088216,"score":68.70373295088216},"GB2-06":{"attempts":3,"playable":41.54818149107941,"score":41.54818149107941},"GB2-07":{"attempts":3,"playable":63.27747842396685,"score":63.27747842396685},"GB2-08":{"attempts":3,"playable":59.502320012164716,"score":59.502320012164716}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":["GB2-02","GB2-06","GB2-08"],"infra_failures_excluded":3,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:05:00Z","losses":4694,"max_score":90.56613075261299,"measured_at":null,"min_score":22.7698174814249,"model_code_failure_rate":0.04,"model_code_failures":1,"model_display_name":"Qwen3.8 Max","model_slug":"qwen-qwen3-8-max","performance_rejected_game_aliases":["GB2-04"],"performance_rejections":1,"plugin_success_rate":null,"provider":"Alibaba","provider_key":"qwen","rank":36,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:50:39Z","ranking_status":"ranked","rated_matches":12264,"rating_method":"bradley_terry_newton","raw_elo":1486.229402664956,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-max","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":50.39499061460254,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":4528},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-luna:ba1f2575d1f25f36","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.014153675,"mean":0.00625249375,"median":0.0043227375,"min":0.00169605,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":16,"boardgame-list-prices-2026-10-09":11},"run_count":24,"token_priced_attempt_count":27,"total":0.15005985},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":3088,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-6-luna","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":23,"first_pass_rate":0.9583333333333334,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":39.05265189796705,"score":39.05265189796705},"GB2-02":{"attempts":3,"playable":50.7509384246112,"score":50.7509384246112},"GB2-03":{"attempts":3,"playable":49.283684192055375,"score":49.283684192055375},"GB2-04":{"attempts":3,"playable":53.3247935991944,"score":53.3247935991944},"GB2-05":{"attempts":3,"playable":46.95227241794306,"score":46.95227241794306},"GB2-06":{"attempts":3,"playable":64.26530201669188,"score":64.26530201669188},"GB2-07":{"attempts":3,"playable":42.18301268298145,"score":42.18301268298145},"GB2-08":{"attempts":3,"playable":46.16118798055593,"score":46.16118798055593}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:39:32Z","losses":5014,"max_score":85.72453199600761,"measured_at":null,"min_score":25.981920227501416,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GPT-6 Luna","model_slug":"gpt-6-luna","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"OpenAI","provider_key":"openai","rank":37,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:53:50Z","ranking_status":"ranked","rated_matches":12264,"rating_method":"bradley_terry_newton","raw_elo":1448.473661888701,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6-luna","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":1,"repaired_rate":0.041666666666666664,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":48.99673040150003,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":4162},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-5:7310f3d9c843d84d","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":39,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":41},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.512955,"mean":0.2537023958333333,"median":0.20905875000000002,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":16,"boardgame-list-prices-2026-10-09":25},"run_count":40,"token_priced_attempt_count":41,"total":11.203785000000002},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":5275,"eligibility_flag":true,"entry_count":39,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"claude-opus-4-5","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":24,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":5,"playable":47.28716580795276,"score":47.28716580795276},"GB2-02":{"attempts":5,"playable":44.01978269800272,"score":44.01978269800272},"GB2-03":{"attempts":4,"playable":47.350346721040445,"score":47.350346721040445},"GB2-04":{"attempts":5,"playable":43.68286333176297,"score":43.68286333176297},"GB2-05":{"attempts":5,"playable":46.55163473624464,"score":46.55163473624464},"GB2-06":{"attempts":5,"playable":48.758492343157336,"score":48.758492343157336},"GB2-07":{"attempts":5,"playable":45.71519328759636,"score":45.71519328759636},"GB2-08":{"attempts":5,"playable":67.69050919036148,"score":67.69050919036148}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:04Z","losses":7994,"max_score":78.1514066074536,"measured_at":null,"min_score":32.34779179198245,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Claude Opus 4.5","model_slug":"claude-opus-4-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Anthropic","provider_key":"anthropic","rank":38,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:17:57Z","ranking_status":"ranked","rated_matches":19946,"rating_method":"bradley_terry_newton","raw_elo":1446.6175406075577,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-4-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":48.88199851451484,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":6677},{"admitted_plugins":23,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k3:8d36d587ce37f8e1","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.6877614000000001,"mean":0.27696257500000004,"median":0.2537256,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":35},"recorded_attempt_count":35,"run_count":24,"total":6.6471018000000015},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2782,"eligibility_flag":true,"entry_count":23,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"moonshotai/kimi-k3","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-06"],"first_pass_admitted":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},"headline_games":{"GB2-01":{"attempts":3,"playable":42.45994842849361,"score":42.45994842849361},"GB2-02":{"attempts":3,"playable":42.134820181371204,"score":42.134820181371204},"GB2-03":{"attempts":3,"playable":64.49684846206823,"score":64.49684846206823},"GB2-04":{"attempts":3,"playable":48.75343845898933,"score":48.75343845898933},"GB2-05":{"attempts":3,"playable":56.39869895365223,"score":56.39869895365223},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":51.9133957045862,"score":34.608930469724136},"GB2-07":{"attempts":3,"playable":48.91728823039659,"score":48.91728823039659},"GB2-08":{"attempts":3,"playable":52.380967227392496,"score":52.380967227392496}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:49Z","losses":4631,"max_score":93.6755483450511,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.041666666666666664,"model_code_failures":1,"model_display_name":"Kimi K3","model_slug":"moonshotai-kimi-k3","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Moonshot","provider_key":"moonshotai","rank":39,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:14:14Z","ranking_status":"ranked","rated_matches":11762,"rating_method":"bradley_terry_newton","raw_elo":1488.1946770782706,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":2,"repaired_rate":0.08333333333333333,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":48.768867551510986,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":4349},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5:1d3023549259b74f","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.15942958333333332,"median":0.068377,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":24},"run_count":24,"token_priced_attempt_count":24,"total":3.826309999999999},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":3061,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"claude-sonnet-5","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":24,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":53.097489202386434,"score":53.097489202386434},"GB2-02":{"attempts":3,"playable":42.91031926256279,"score":42.91031926256279},"GB2-03":{"attempts":3,"playable":52.944088155510975,"score":52.944088155510975},"GB2-04":{"attempts":3,"playable":47.36142387062464,"score":47.36142387062464},"GB2-05":{"attempts":3,"playable":40.34383703427311,"score":40.34383703427311},"GB2-06":{"attempts":3,"playable":38.90758686910235,"score":38.90758686910235},"GB2-07":{"attempts":3,"playable":51.43130291656032,"score":51.43130291656032},"GB2-08":{"attempts":3,"playable":57.91504898752631,"score":57.91504898752631}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:41Z","losses":5129,"max_score":81.4911023882058,"measured_at":null,"min_score":23.342125558174647,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Claude Sonnet 5","model_slug":"claude-sonnet-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Anthropic","provider_key":"anthropic","rank":40,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:18:32Z","ranking_status":"ranked","rated_matches":12264,"rating_method":"bradley_terry_newton","raw_elo":1424.243911869553,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-sonnet-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":48.113887037318364,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":4074},{"admitted_plugins":16,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:inception-mercury-3:6a2a7db9e6b297ec","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":24,"cost_basis_counts":{"provider_reported":31},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.08221237,"mean":0.028891608750000006,"median":0.03513247,"min":0.0015762,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":24},"recorded_attempt_count":31,"run_count":24,"total":0.69339861},"codegen_evaluated_cells":17,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2052,"eligibility_flag":false,"entry_count":16,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"inception/mercury-3","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03"],"first_pass_admitted":11,"first_pass_rate":0.6470588235294118,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":42.474188829410735,"score":42.474188829410735},"GB2-02":{"attempts":3,"playable":44.423290865053616,"score":44.423290865053616},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":47.92005544149431,"score":31.946703627662874},"GB2-04":{"attempts":1,"playable":40.67743529617756,"score":40.67743529617756},"GB2-05":{"attempts":1,"playable":25.26458038695291,"score":25.26458038695291},"GB2-06":{"attempts":2,"playable":73.26054566875459,"score":73.26054566875459},"GB2-07":{"attempts":2,"playable":55.69663845552597,"score":55.69663845552597},"GB2-08":{"attempts":3,"playable":50.388693278788914,"score":50.388693278788914}},"ineligibility_reason_codes":["generation_incomplete"],"infra_excluded_game_aliases":["GB2-01","GB2-04","GB2-05","GB2-06","GB2-07"],"infra_failures_excluded":7,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:37:40Z","losses":3304,"max_score":79.63955354616625,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.058823529411764705,"model_code_failures":1,"model_display_name":"Mercury 3","model_slug":"inception-mercury-3","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Inception","provider_key":"inception","rank":41,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"partial","rated_matches":8165,"rating_method":"bradley_terry_newton","raw_elo":1417.6057257170496,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inception","provider_model":"inception/mercury-3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":5,"repaired_rate":0.29411764705882354,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":47.818711234817805,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":2809},{"admitted_plugins":23,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-terra:44bc2ca1b1081818","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.45800250000000003,"mean":0.18569479166666666,"median":0.091314375,"min":0.058876874999999995,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":28},"run_count":24,"token_priced_attempt_count":28,"total":4.456675000000001},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":3246,"eligibility_flag":true,"entry_count":23,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.6-terra","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-05"],"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},"headline_games":{"GB2-01":{"attempts":3,"playable":67.9879135416809,"score":67.9879135416809},"GB2-02":{"attempts":3,"playable":50.03946358562255,"score":50.03946358562255},"GB2-03":{"attempts":3,"playable":34.807584793612236,"score":34.807584793612236},"GB2-04":{"attempts":3,"playable":43.53679970301437,"score":43.53679970301437},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":56.980135114635516,"score":37.986756743090346},"GB2-06":{"attempts":3,"playable":53.35798524194211,"score":53.35798524194211},"GB2-07":{"attempts":3,"playable":44.932025896483346,"score":44.932025896483346},"GB2-08":{"attempts":3,"playable":45.157099700148336,"score":45.157099700148336}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:54:15Z","losses":4617,"max_score":80.7302675590266,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.041666666666666664,"model_code_failures":1,"model_display_name":"GPT-5.6 Terra","model_slug":"gpt-5-6-terra","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"OpenAI","provider_key":"openai","rank":42,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:15:32Z","ranking_status":"ranked","rated_matches":11735,"rating_method":"bradley_terry_newton","raw_elo":1437.4101595417526,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-terra","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":3,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":47.22570365069927,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":3872},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:gemini-3-1-pro-preview:4c28af42c705817c","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.46894399999999997,"mean":0.15006158333333333,"median":0.080065,"min":0.035026,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"run_count":24,"token_priced_attempt_count":28,"total":3.6014779999999997},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2788,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"google","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"gemini-3.1-pro-preview","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":20,"first_pass_rate":0.8333333333333334,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":50.14465808232043,"score":50.14465808232043},"GB2-02":{"attempts":3,"playable":43.57936484085988,"score":43.57936484085988},"GB2-03":{"attempts":3,"playable":53.934586152255015,"score":53.934586152255015},"GB2-04":{"attempts":3,"playable":56.417089976376325,"score":56.417089976376325},"GB2-05":{"attempts":3,"playable":39.60273081716763,"score":39.60273081716763},"GB2-06":{"attempts":3,"playable":21.315492922941452,"score":21.315492922941452},"GB2-07":{"attempts":3,"playable":56.82168142023283,"score":56.82168142023283},"GB2-08":{"attempts":3,"playable":48.095526796403156,"score":48.095526796403156}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:54:15Z","losses":5443,"max_score":85.87456832444144,"measured_at":null,"min_score":14.965279068230211,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Gemini 3.1 Pro Preview","model_slug":"gemini-3-1-pro-preview","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Google","provider_key":"google","rank":43,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:46:30Z","ranking_status":"ranked","rated_matches":12264,"rating_method":"bradley_terry_newton","raw_elo":1401.4639437788053,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"gemini-3.1-pro-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"google","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":4,"repaired_rate":0.16666666666666666,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":46.238891376069596,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":4033},{"admitted_plugins":22,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:reflection-beam-1-0-501b-a23b:b81a4fc36a279e88","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":36},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.04917425,"mean":0.015867427083333333,"median":0.01165575,"min":0.0040545,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":36},"recorded_attempt_count":36,"run_count":24,"total":0.38081825000000014},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2497,"eligibility_flag":true,"entry_count":22,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"reflection/beam-1.0-501b-a23b","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-06"],"first_pass_admitted":13,"first_pass_rate":0.5416666666666666,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":33.95312522498125,"score":22.635416816654168},"GB2-02":{"attempts":3,"playable":43.20367362278705,"score":43.20367362278705},"GB2-03":{"attempts":3,"playable":53.94951466976156,"score":53.94951466976156},"GB2-04":{"attempts":3,"playable":46.973032543533556,"score":46.973032543533556},"GB2-05":{"attempts":3,"playable":52.050134165299305,"score":52.050134165299305},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":65.19966332932201,"score":43.46644221954801},"GB2-07":{"attempts":3,"playable":26.91130255177551,"score":26.91130255177551},"GB2-08":{"attempts":3,"playable":68.58940829603792,"score":68.58940829603792}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:57Z","losses":4767,"max_score":82.65322900116001,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.08333333333333333,"model_code_failures":2,"model_display_name":"Beam 1.0 501B A23B","model_slug":"reflection-beam-1-0-501b-a23b","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Other","provider_key":"other","rank":44,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:07:57Z","ranking_status":"ranked","rated_matches":11245,"rating_method":"bradley_terry_newton","raw_elo":1437.0370608754213,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"reflection/beam-1.0-501b-a23b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":9,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":44.722365610674636,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":3981},{"admitted_plugins":48,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-2:6d2033982d88524b","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":48,"cell_count":24,"cost_basis_counts":{"provider_reported":72},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.09944282164861112,"median":0.056673037849999996,"min":0.013816857666666668,"recorded_attempt_count":72,"run_count":48,"total":3.5146565168},"codegen_evaluated_cells":48,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":6599,"eligibility_flag":true,"entry_count":48,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"z-ai/glm-5.2","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":26,"first_pass_rate":0.5416666666666666,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":6,"playable":40.56650772953453,"score":40.56650772953453},"GB2-02":{"attempts":6,"playable":50.65472668569851,"score":50.65472668569851},"GB2-03":{"attempts":6,"playable":35.99552912349877,"score":35.99552912349877},"GB2-04":{"attempts":6,"playable":50.00389491093432,"score":50.00389491093432},"GB2-05":{"attempts":6,"playable":49.4397351448528,"score":49.4397351448528},"GB2-06":{"attempts":6,"playable":55.887916627661006,"score":55.887916627661006},"GB2-07":{"attempts":6,"playable":38.958972619779836,"score":38.958972619779836},"GB2-08":{"attempts":6,"playable":34.60002259558937,"score":34.60002259558937}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:54Z","losses":11006,"max_score":78.72629412605932,"measured_at":null,"min_score":10.34922351327472,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GLM-5.2","model_slug":"z-ai-glm-5-2","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Zhipu","provider_key":"z-ai","rank":45,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:20:20Z","ranking_status":"ranked","rated_matches":24528,"rating_method":"bradley_terry_newton","raw_elo":1388.7040586480744,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.2","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":22,"repaired_rate":0.4583333333333333,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":44.513413179693636,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":6923},{"admitted_plugins":22,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro-0813:9ff71329b8b2ecbf","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":31},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.28337826924,"mean":0.09905735158166666,"median":0.10177922040000001,"min":0.01808105112,"recorded_attempt_count":31,"run_count":24,"total":2.37737643796},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2540,"eligibility_flag":true,"entry_count":22,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4-pro-0813","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-05"],"first_pass_admitted":18,"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},"headline_games":{"GB2-01":{"attempts":3,"playable":43.564494832612546,"score":43.564494832612546},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.961185984424674,"score":28.640790656283116},"GB2-03":{"attempts":3,"playable":47.81425062042686,"score":47.81425062042686},"GB2-04":{"attempts":3,"playable":40.59883613538042,"score":40.59883613538042},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":59.67350852696781,"score":39.782339017978536},"GB2-06":{"attempts":3,"playable":55.636095484433945,"score":55.636095484433945},"GB2-07":{"attempts":3,"playable":58.9215429215626,"score":58.9215429215626},"GB2-08":{"attempts":3,"playable":35.25141331438848,"score":35.25141331438848}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T00:22:44Z","losses":4870,"max_score":79.27457840265981,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.08333333333333333,"model_code_failures":2,"model_display_name":"DeepSeek V4 Pro 0813","model_slug":"deepseek-deepseek-v4-pro-0813","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"DeepSeek","provider_key":"deepseek","rank":46,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:18:37Z","ranking_status":"ranked","rated_matches":11254,"rating_method":"bradley_terry_newton","raw_elo":1424.8937463386467,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-pro-0813","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":4,"repaired_rate":0.16666666666666666,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":43.77622037288331,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":3844},{"admitted_plugins":22,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro:b44807291d543f40","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.176790095,"mean":0.062023549123500006,"median":0.0458058365,"min":0.014466934,"recorded_attempt_count":35,"run_count":24,"total":1.4885651789640002},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2579,"eligibility_flag":true,"entry_count":22,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4-pro","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-06"],"first_pass_admitted":13,"first_pass_rate":0.5416666666666666,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":39.65244020354163,"score":39.65244020354163},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.53512890742101,"score":28.356752604947342},"GB2-03":{"attempts":3,"playable":39.58544442636555,"score":39.58544442636555},"GB2-04":{"attempts":3,"playable":45.33701969516898,"score":45.33701969516898},"GB2-05":{"attempts":3,"playable":42.923426735963524,"score":42.923426735963524},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":63.688101908464226,"score":42.45873460564282},"GB2-07":{"attempts":3,"playable":66.88044783195903,"score":66.88044783195903},"GB2-08":{"attempts":3,"playable":43.0284499513531,"score":43.0284499513531}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:40:16Z","losses":4860,"max_score":84.47322859681222,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.08333333333333333,"model_code_failures":2,"model_display_name":"DeepSeek V4 Pro","model_slug":"deepseek-deepseek-v4-pro","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"DeepSeek","provider_key":"deepseek","rank":47,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:45:04Z","ranking_status":"ranked","rated_matches":11281,"rating_method":"bradley_terry_newton","raw_elo":1425.6973343415566,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":9,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":43.52783950686774,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":3842},{"admitted_plugins":21,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:gpt-5:9c328f26eed06df1","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":31},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":0.45464499999999997,"mean":0.18566328125000006,"median":0.17276625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12,"boardgame-list-prices-2026-10-09":19},"run_count":24,"token_priced_attempt_count":31,"total":4.4559187499999995},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2406,"eligibility_flag":false,"entry_count":21,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02"],"first_pass_admitted":16,"first_pass_rate":0.7272727272727273,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":43.81384099393201,"score":43.81384099393201},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":40.47457594530332,"score":26.983050630202214},"GB2-03":{"attempts":3,"playable":28.405643914502928,"score":28.405643914502928},"GB2-04":{"attempts":2,"playable":41.44331354005614,"score":41.44331354005614},"GB2-05":{"attempts":3,"playable":61.7506949190068,"score":61.7506949190068},"GB2-06":{"attempts":2,"playable":59.530548523954785,"score":59.530548523954785},"GB2-07":{"attempts":3,"playable":52.412531555784916,"score":52.412531555784916},"GB2-08":{"attempts":3,"playable":37.23832745421451,"score":37.23832745421451}},"ineligibility_reason_codes":["untested_or_ineligible_settings"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T00:59:53Z","losses":4916,"max_score":75.91303436651312,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.045454545454545456,"model_code_failures":1,"model_display_name":"GPT-5","model_slug":"gpt-5","performance_rejected_game_aliases":["GB2-04","GB2-06"],"performance_rejections":2,"plugin_success_rate":null,"provider":"OpenAI","provider_key":"openai","rank":48,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"partial","rated_matches":10784,"rating_method":"bradley_terry_newton","raw_elo":1393.038157023884,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":5,"repaired_rate":0.22727272727272727,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":43.199946457290686,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":3462},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-luna:bdb834bbe44b790a","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.01391661875,"median":0.00586915,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":0.3339988500000001},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":3511,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.6-luna","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":23,"first_pass_rate":0.9583333333333334,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":51.3498744762477,"score":51.3498744762477},"GB2-02":{"attempts":3,"playable":43.71985904429773,"score":43.71985904429773},"GB2-03":{"attempts":3,"playable":38.58202493672601,"score":38.58202493672601},"GB2-04":{"attempts":3,"playable":41.75912050300873,"score":41.75912050300873},"GB2-05":{"attempts":3,"playable":40.09466295264844,"score":40.09466295264844},"GB2-06":{"attempts":3,"playable":52.569411071694226,"score":52.569411071694226},"GB2-07":{"attempts":3,"playable":38.80257986929555,"score":38.80257986929555},"GB2-08":{"attempts":3,"playable":25.773265276263725,"score":25.773265276263725}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:54:42Z","losses":5686,"max_score":83.72858164014411,"measured_at":null,"min_score":10.977083083894604,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GPT-5.6 Luna","model_slug":"gpt-5-6-luna","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"OpenAI","provider_key":"openai","rank":49,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:07:02Z","ranking_status":"ranked","rated_matches":12264,"rating_method":"bradley_terry_newton","raw_elo":1356.1743770217663,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-luna","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":1,"repaired_rate":0.041666666666666664,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":41.581349766272766,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":3067},{"admitted_plugins":21,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:minimax-minimax-m3-1-flash:02aee399a5efb5d8","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":35},"recorded_attempt_count":35,"run_count":24,"total":0.0},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2213,"eligibility_flag":false,"entry_count":21,"evaluated_setting_identity":{"canonical_provider_route":"unknown_legacy","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"minimax/minimax-m3.1-flash","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-08"],"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},"headline_games":{"GB2-01":{"attempts":3,"playable":37.984877796527435,"score":37.984877796527435},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":41.42939693014983,"score":27.619597953433217},"GB2-03":{"attempts":3,"playable":34.826379796640076,"score":34.826379796640076},"GB2-04":{"attempts":3,"playable":39.68806985319623,"score":39.68806985319623},"GB2-05":{"attempts":3,"playable":48.93470138678226,"score":48.93470138678226},"GB2-06":{"attempts":3,"playable":51.182489328590215,"score":51.182489328590215},"GB2-07":{"attempts":3,"playable":54.64746639978847,"score":54.64746639978847},"GB2-08":{"attempts":3,"failed_attempts":2,"playable":29.05883933830283,"score":9.686279779434276}},"ineligibility_reason_codes":["unknown_capability_evidence"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:50:17Z","losses":5166,"max_score":72.78229423571837,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":3,"model_display_name":"Minimax M3.1 Flash","model_slug":"minimax-minimax-m3-1-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"MiniMax","provider_key":"minimax","rank":50,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"partial","rated_matches":10706,"rating_method":"bradley_terry_newton","raw_elo":1401.4003402140354,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"minimax","provider_model":"minimax/minimax-m3.1-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":7,"repaired_rate":0.2916666666666667,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":38.07123278679902,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":3327},{"admitted_plugins":22,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:bytedance-seed-seed-2-0-code:a3960c506262e9f0","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.075846,"mean":0.041728458333333336,"median":0.04202725,"min":0.0121355,"recorded_attempt_count":34,"run_count":24,"total":1.0014829999999997},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2800,"eligibility_flag":true,"entry_count":22,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"bytedance-seed/seed-2.0-code","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-07"],"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},"headline_games":{"GB2-01":{"attempts":3,"playable":38.689791152987624,"score":38.689791152987624},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":40.26392443461065,"score":26.842616289740434},"GB2-03":{"attempts":3,"playable":42.68953433131849,"score":42.68953433131849},"GB2-04":{"attempts":3,"playable":40.67602002741477,"score":40.67602002741477},"GB2-05":{"attempts":3,"playable":38.36891427996026,"score":38.36891427996026},"GB2-06":{"attempts":3,"playable":17.503696495344197,"score":17.503696495344197},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":37.04158353467015,"score":24.694389023113434},"GB2-08":{"attempts":3,"playable":62.032659715708654,"score":62.032659715708654}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:43Z","losses":5615,"max_score":86.94320232424666,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.08333333333333333,"model_code_failures":2,"model_display_name":"Seed 2.0 Code","model_slug":"bytedance-seed-seed-2-0-code","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"ByteDance","provider_key":"bytedance-seed","rank":51,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:21:15Z","ranking_status":"ranked","rated_matches":11254,"rating_method":"bradley_terry_newton","raw_elo":1322.739667654326,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"bytedance-seed","provider_model":"bytedance-seed/seed-2.0-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":8,"repaired_rate":0.3333333333333333,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":36.437202664448485,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":2839},{"admitted_plugins":33,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:o3:6e7cd0e8fff13a95","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":33,"cell_count":24,"cost_basis_counts":{"estimated":32,"local_standard_estimate":26},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":15,"max":0.1097735,"mean":0.06116525,"median":0.054719000000000004,"min":0.030172,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":58},"recorded_attempt_count":32,"run_count":48,"token_priced_attempt_count":26,"total":3.663629999999999},"codegen_evaluated_cells":48,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2202,"eligibility_flag":true,"entry_count":33,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"o3","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-08"],"first_pass_admitted":32,"first_pass_rate":0.7272727272727273,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":6,"failed_attempts":1,"playable":45.37979239589587,"score":40.31176576452305},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":42.487598451954895,"score":21.243799225977448},"GB2-03":{"attempts":6,"failed_attempts":4,"playable":39.080886955246186,"score":16.99596809251327},"GB2-04":{"attempts":6,"failed_attempts":4,"playable":42.9235838167643,"score":28.615722544509534},"GB2-05":{"attempts":6,"playable":48.397945071952115,"score":48.397945071952115},"GB2-06":{"attempts":6,"playable":44.87884802518503,"score":44.87884802518503},"GB2-07":{"attempts":6,"playable":47.08329360060379,"score":47.08329360060379},"GB2-08":{"attempts":6,"failed_attempts":1,"playable":42.7400443845234,"score":38.754408187321175}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:04Z","losses":8608,"max_score":58.72681136385298,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":11,"model_display_name":"o3","model_slug":"o3","performance_rejected_game_aliases":["GB2-02"],"performance_rejections":4,"plugin_success_rate":null,"provider":"OpenAI","provider_key":"openai","rank":52,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T18:09:41Z","ranking_status":"ranked","rated_matches":17106,"rating_method":"bradley_terry_newton","raw_elo":1383.6526869370223,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"o3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":1,"repaired_rate":0.022727272727272728,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":36.235655526526436,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":6296},{"admitted_plugins":17,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-27b:cd2b67dff13967b7","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":24,"cost_basis_counts":{"provider_reported":38},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.3521656,"mean":0.08720021666666666,"median":0.0402421875,"min":0.00651321,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":27},"recorded_attempt_count":38,"run_count":24,"total":2.0928052},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":1876,"eligibility_flag":false,"entry_count":17,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.8-27b","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-03","GB2-04","GB2-05","GB2-07","GB2-08"],"first_pass_admitted":11,"first_pass_rate":0.4583333333333333,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":50.90554664525774,"score":50.90554664525774},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.06446832874224,"score":28.04297888582816},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":45.82290792279751,"score":30.548605281865008},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":55.62007741806809,"score":37.080051612045395},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":59.262151563671,"score":39.50810104244733},"GB2-06":{"attempts":3,"playable":40.46175290498238,"score":40.46175290498238},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":49.638088061840136,"score":33.09205870789342},"GB2-08":{"attempts":3,"failed_attempts":2,"playable":51.320974875694716,"score":17.106991625231572}},"ineligibility_reason_codes":["below_generation_quality_threshold"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:27:38Z","losses":3690,"max_score":78.23975127005579,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.2916666666666667,"model_code_failures":7,"model_display_name":"Qwen3.8 27B","model_slug":"qwen-qwen3-8-27b","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Alibaba","provider_key":"qwen","rank":53,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"partial","rated_matches":8656,"rating_method":"bradley_terry_newton","raw_elo":1379.603415910634,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-27b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":6,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":34.59326083819388,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":3090},{"admitted_plugins":36,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-flash:f53ed4c014b59525","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":36,"cell_count":24,"cost_basis_counts":{"provider_reported":59},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.01423672,"mean":0.004144189362222222,"median":0.0032265161666666666,"min":0.0008945895,"recorded_attempt_count":59,"run_count":40,"total":0.16008749804},"codegen_evaluated_cells":38,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":4601,"eligibility_flag":true,"entry_count":36,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4-flash","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-04","GB2-05"],"first_pass_admitted":25,"first_pass_rate":0.6578947368421053,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":5,"playable":24.865429877193744,"score":24.865429877193744},"GB2-02":{"attempts":5,"playable":41.48573833052928,"score":41.48573833052928},"GB2-03":{"attempts":4,"playable":37.86568196557769,"score":37.86568196557769},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":41.59709508256233,"score":27.731396721708222},"GB2-05":{"attempts":5,"failed_attempts":1,"playable":35.32858348369627,"score":23.552388989130847},"GB2-06":{"attempts":5,"playable":54.83006983594731,"score":54.83006983594731},"GB2-07":{"attempts":5,"playable":27.97527869177901,"score":27.97527869177901},"GB2-08":{"attempts":5,"playable":35.3006340909978,"score":35.3006340909978}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":["GB2-03","GB2-04"],"infra_failures_excluded":2,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:04:59Z","losses":9936,"max_score":82.0934769045649,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.05263157894736842,"model_code_failures":2,"model_display_name":"DeepSeek V4 Flash","model_slug":"deepseek-deepseek-v4-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"DeepSeek","provider_key":"deepseek","rank":54,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:06:59Z","ranking_status":"ranked","rated_matches":18421,"rating_method":"bradley_terry_newton","raw_elo":1303.1828537139957,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":11,"repaired_rate":0.2894736842105263,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":34.20082731285799,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":3884},{"admitted_plugins":19,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:stealth-space-bunny-alpha:67ba69ad004706a8","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":19,"cell_count":24,"cost_basis_counts":{"provider_reported":42},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":42},"recorded_attempt_count":42,"run_count":24,"total":0.0},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2396,"eligibility_flag":true,"entry_count":19,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"stealth/space-bunny-alpha","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-06","GB2-08"],"first_pass_admitted":7,"first_pass_rate":0.2916666666666667,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":56.5764097745617,"score":37.71760651637447},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":41.79952124297172,"score":27.866347495314482},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":40.90207894746507,"score":27.268052631643382},"GB2-04":{"attempts":3,"playable":41.18664500659943,"score":41.18664500659943},"GB2-05":{"attempts":3,"playable":34.14413371354145,"score":34.14413371354145},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":48.505551651737775,"score":32.33703443449185},"GB2-07":{"attempts":3,"playable":45.52100312227699,"score":45.52100312227699},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":32.08191972809129,"score":21.387946485394195}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:58Z","losses":4653,"max_score":74.43144469769753,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.20833333333333334,"model_code_failures":5,"model_display_name":"Space Bunny Alpha","model_slug":"stealth-space-bunny-alpha","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Other","provider_key":"other","rank":55,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:02:40Z","ranking_status":"ranked","rated_matches":9734,"rating_method":"bradley_terry_newton","raw_elo":1336.9130510033744,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"stealth/space-bunny-alpha","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":12,"repaired_rate":0.5,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":33.428596175704534,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":2685},{"admitted_plugins":43,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash-lite:12939bf008fc0164","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":43,"cell_count":24,"cost_basis_counts":{"provider_reported":132},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0719635,"mean":0.03858281041666666,"median":0.037386975,"min":0.012759,"recorded_attempt_count":132,"run_count":48,"total":1.8519749},"codegen_evaluated_cells":48,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":5335,"eligibility_flag":true,"entry_count":42,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.5-flash-lite","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-07"],"first_pass_admitted":36,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":6,"failed_attempts":1,"playable":37.705424753578335,"score":31.841360231998504},"GB2-02":{"attempts":6,"failed_attempts":2,"playable":43.13507341987674,"score":28.338718830081707},"GB2-03":{"attempts":6,"failed_attempts":1,"playable":48.293481127523016,"score":39.09496197417404},"GB2-04":{"attempts":6,"playable":43.08944591636314,"score":43.08944591636314},"GB2-05":{"attempts":6,"playable":15.248357952159784,"score":15.248357952159784},"GB2-06":{"attempts":6,"playable":37.239279692158796,"score":37.239279692158796},"GB2-07":{"attempts":6,"failed_attempts":1,"playable":42.558152791836825,"score":39.085118603835596},"GB2-08":{"attempts":6,"playable":30.843423608113195,"score":30.843423608113195}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:49Z","losses":11373,"max_score":62.104276468822164,"measured_at":null,"min_score":10.419102564003692,"model_code_failure_rate":0.10416666666666667,"model_code_failures":5,"model_display_name":"Gemini 3.5 Flash Lite","model_slug":"google-gemini-3-5-flash-lite","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Google","provider_key":"google","rank":56,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:12:16Z","ranking_status":"ranked","rated_matches":21489,"rating_method":"bradley_terry_newton","raw_elo":1283.7165600952987,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.5-flash-lite","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":7,"repaired_rate":0.14583333333333334,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":33.09758335111059,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":4781},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling-small:8b9ac06aa7e2af6c","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":43},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.06806129999999999,"mean":0.01775885625,"median":0.0102184875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":43},"recorded_attempt_count":43,"run_count":28,"total":0.5373185999999999},"codegen_evaluated_cells":28,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":3379,"eligibility_flag":true,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"thinkingmachines/inkling-small","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-04","GB2-06"],"first_pass_admitted":15,"first_pass_rate":0.5555555555555556,"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},"headline_games":{"GB2-01":{"attempts":3,"playable":21.47918166611663,"score":21.47918166611663},"GB2-02":{"attempts":3,"playable":41.74687276729588,"score":41.74687276729588},"GB2-03":{"attempts":3,"playable":47.54102928298632,"score":47.54102928298632},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":43.77451720646989,"score":36.722425501752},"GB2-05":{"attempts":3,"playable":19.136076121949344,"score":19.136076121949344},"GB2-06":{"attempts":5,"failed_attempts":2,"playable":29.671586185149867,"score":23.922328633066357},"GB2-07":{"attempts":3,"playable":35.47872248762044,"score":35.47872248762044},"GB2-08":{"attempts":3,"playable":28.329572106248346,"score":28.329572106248346}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:44Z","losses":6774,"max_score":56.9002243892639,"measured_at":null,"min_score":5.47119175608054,"model_code_failure_rate":0.1111111111111111,"model_code_failures":3,"model_display_name":"Inkling Small","model_slug":"thinkingmachines-inkling-small","performance_rejected_game_aliases":["GB2-06"],"performance_rejections":1,"plugin_success_rate":null,"provider":"Thinking Machines","provider_key":"thinkingmachines","rank":57,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:01:26Z","ranking_status":"ranked","rated_matches":12264,"rating_method":"bradley_terry_newton","raw_elo":1228.3841270004034,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"thinkingmachines","provider_model":"thinkingmachines/inkling-small","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":9,"repaired_rate":0.3333333333333333,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":31.794526070879414,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":2111},{"admitted_plugins":21,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-glimmer-30b:97778464fdf4bc27","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.02351982,"mean":0.011764807916666668,"median":0.0084872,"min":0.00402612,"recorded_attempt_count":34,"run_count":24,"total":0.28235539},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":3163,"eligibility_flag":true,"entry_count":21,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-glimmer-30b","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-06"],"first_pass_admitted":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},"headline_games":{"GB2-01":{"attempts":3,"playable":29.995757715173156,"score":29.995757715173156},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":43.22759991228898,"score":28.818399941525985},"GB2-03":{"attempts":3,"playable":40.65907175548377,"score":40.65907175548377},"GB2-04":{"attempts":3,"playable":46.08079421319206,"score":46.08079421319206},"GB2-05":{"attempts":3,"playable":23.047355482438387,"score":23.047355482438387},"GB2-06":{"attempts":3,"failed_attempts":2,"playable":17.1342988476045,"score":5.711432949201501},"GB2-07":{"attempts":3,"playable":37.474346284011766,"score":37.474346284011766},"GB2-08":{"attempts":3,"playable":30.678351855415784,"score":30.678351855415784}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:59:42Z","losses":5716,"max_score":49.231658345772594,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":3,"model_display_name":"Muse Glimmer 30B","model_slug":"meta-muse-glimmer-30b","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Meta","provider_key":"meta","rank":58,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:34:55Z","ranking_status":"ranked","rated_matches":10779,"rating_method":"bradley_terry_newton","raw_elo":1256.176246684084,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-glimmer-30b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":7,"repaired_rate":0.2916666666666667,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":30.308188774555305,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":1900},{"admitted_plugins":21,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:openai-gpt-oss-120b:f7b7ca6843818cf7","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":33},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.015120192000000001,"mean":0.0032700552500000003,"median":0.0013951725,"min":0.00046744,"recorded_attempt_count":33,"run_count":24,"total":0.07848132600000002},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2950,"eligibility_flag":true,"entry_count":21,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"openai/gpt-oss-120b","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-04","GB2-06"],"first_pass_admitted":16,"first_pass_rate":0.6666666666666666,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":38.49949571858879,"score":25.666330479059194},"GB2-02":{"attempts":3,"playable":43.22745599184024,"score":43.22745599184024},"GB2-03":{"attempts":3,"playable":39.55240287209788,"score":39.55240287209788},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":40.72709435494931,"score":27.151396236632873},"GB2-05":{"attempts":3,"playable":29.880770757423324,"score":29.880770757423324},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":24.759964175155375,"score":16.506642783436916},"GB2-07":{"attempts":3,"playable":28.06058758590523,"score":28.06058758590523},"GB2-08":{"attempts":3,"playable":31.668936655480177,"score":31.668936655480177}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:43Z","losses":5827,"max_score":58.31249676882345,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":3,"model_display_name":"GPT-OSS 120B","model_slug":"openai-gpt-oss-120b","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"OpenAI","provider_key":"openai","rank":59,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:06:59Z","ranking_status":"ranked","rated_matches":10748,"rating_method":"bradley_terry_newton","raw_elo":1247.6777120001177,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"openai/gpt-oss-120b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":5,"repaired_rate":0.20833333333333334,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":30.214315420234474,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":1971},{"admitted_plugins":21,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:nvidia-nemotron-3-ultra-550b-a55b:9c0592db82206e94","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":70},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.13485595000000003,"mean":0.03294963020833334,"median":0.02851355,"min":0.0111232,"recorded_attempt_count":70,"run_count":34,"total":1.2116408500000002},"codegen_evaluated_cells":30,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":3041,"eligibility_flag":false,"entry_count":21,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"nvidia/nemotron-3-ultra-550b-a55b","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-07"],"first_pass_admitted":7,"first_pass_rate":0.23333333333333334,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":4,"failed_attempts":1,"playable":46.01209872760595,"score":41.74292947169953},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":40.97888885415118,"score":27.319259236100788},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":30.557911384038643,"score":10.185970461346214},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":41.75061437505168,"score":27.833742916701123},"GB2-05":{"attempts":3,"playable":46.09757293123491,"score":46.09757293123491},"GB2-06":{"attempts":3,"playable":35.635890749024405,"score":35.635890749024405},"GB2-07":{"attempts":5,"failed_attempts":3,"playable":7.444611419960019,"score":4.13784593552744},"GB2-08":{"attempts":4,"playable":31.833932146934472,"score":31.833932146934472}},"ineligibility_reason_codes":["untested_or_ineligible_settings","generation_incomplete"],"infra_excluded_game_aliases":["GB2-04","GB2-05","GB2-06"],"infra_failures_excluded":4,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:55:48Z","losses":5673,"max_score":61.9150209611777,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.3,"model_code_failures":9,"model_display_name":"Nemotron 3 Ultra 550B A55B","model_slug":"nvidia-nemotron-3-ultra-550b-a55b","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"NVIDIA","provider_key":"nvidia","rank":60,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"partial","rated_matches":10786,"rating_method":"bradley_terry_newton","raw_elo":1272.1459236594612,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nvidia","provider_model":"nvidia/nemotron-3-ultra-550b-a55b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":14,"repaired_rate":0.4666666666666667,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":27.332375234422283,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":2072},{"admitted_plugins":32,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling:ccc5a8a54a03baa4","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":32,"cell_count":24,"cost_basis_counts":{"provider_reported":112},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.261503015,"mean":0.09751241583333332,"median":0.042993304999999996,"min":0.01737051,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":112,"run_count":46,"total":5.74391615},"codegen_evaluated_cells":40,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":4195,"eligibility_flag":true,"entry_count":32,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"thinkingmachines/inkling","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-04","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":20,"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},"headline_games":{"GB2-01":{"attempts":5,"playable":25.980649336302065,"score":25.980649336302065},"GB2-02":{"attempts":5,"failed_attempts":2,"playable":42.936414729034176,"score":21.296430573015243},"GB2-03":{"attempts":5,"playable":44.74522943810561,"score":44.74522943810561},"GB2-04":{"attempts":5,"failed_attempts":1,"playable":42.34534240435115,"score":35.0041696164127},"GB2-05":{"attempts":5,"playable":19.284277946521605,"score":19.284277946521605},"GB2-06":{"attempts":5,"failed_attempts":2,"playable":35.0826287198967,"score":21.558643744116495},"GB2-07":{"attempts":5,"failed_attempts":1,"playable":23.743081235160133,"score":19.809290204031043},"GB2-08":{"attempts":5,"failed_attempts":2,"playable":56.74783978639129,"score":25.710920208617022}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-07","GB2-08"],"infra_failures_excluded":6,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:25Z","losses":8912,"max_score":49.256787729934594,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.2,"model_code_failures":8,"model_display_name":"Inkling","model_slug":"thinkingmachines-inkling","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Thinking Machines","provider_key":"thinkingmachines","rank":61,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:04:18Z","ranking_status":"ranked","rated_matches":16372,"rating_method":"bradley_terry_newton","raw_elo":1215.7913894165968,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"thinkingmachines","provider_model":"thinkingmachines/inkling","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":12,"repaired_rate":0.3,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":26.673701383390227,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":3265},{"admitted_plugins":17,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-3-7-flash:eb076fe7c5397a32","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":24,"cost_basis_counts":{"provider_reported":46},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.11219570000000001,"mean":0.030692482499999996,"median":0.01928415,"min":0.00650197,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":26},"recorded_attempt_count":46,"run_count":24,"total":0.73661958},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":1620,"eligibility_flag":true,"entry_count":17,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"stepfun/step-3.7-flash","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-03","GB2-04","GB2-05","GB2-08"],"first_pass_admitted":7,"first_pass_rate":0.2916666666666667,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":17.700345925244225,"score":17.700345925244225},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":43.54460209735465,"score":14.514867365784882},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":36.123448745573626,"score":24.08229916371575},"GB2-04":{"attempts":3,"failed_attempts":2,"playable":40.16595143167495,"score":13.388650477224983},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":45.00661836879158,"score":30.00441224586105},"GB2-06":{"attempts":3,"playable":42.56506207885854,"score":42.56506207885854},"GB2-07":{"attempts":3,"playable":35.089379817859665,"score":35.089379817859665},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":24.189244584591044,"score":16.12616305639403}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T23:55:10Z","losses":5173,"max_score":50.6790792678975,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.2916666666666667,"model_code_failures":7,"model_display_name":"Step 3.7 Flash","model_slug":"stepfun-step-3-7-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"StepFun","provider_key":"stepfun","rank":62,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T16:58:20Z","ranking_status":"ranked","rated_matches":8746,"rating_method":"bradley_terry_newton","raw_elo":1217.8200165284334,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"stepfun","provider_model":"stepfun/step-3.7-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":10,"repaired_rate":0.4166666666666667,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":24.183897516367892,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":1953},{"admitted_plugins":17,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:inception-mercury-2-5-preview:734104767af6fe82","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":24,"cost_basis_counts":{"provider_reported":37},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0025894200000000003,"mean":0.0011797070833333334,"median":0.000945325,"min":0.00044038,"recorded_attempt_count":37,"run_count":24,"total":0.028312970000000003},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2957,"eligibility_flag":true,"entry_count":17,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"inception/mercury-2.5-preview","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-03","GB2-05","GB2-07","GB2-08"],"first_pass_admitted":13,"first_pass_rate":0.5416666666666666,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"failed_attempts":2,"playable":27.416518712100512,"score":9.13883957070017},"GB2-02":{"attempts":3,"playable":42.66376026560186,"score":42.66376026560186},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":45.99221229282847,"score":15.330737430942824},"GB2-04":{"attempts":3,"playable":41.28886531507201,"score":41.28886531507201},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":28.267788382598997,"score":18.845192255066},"GB2-06":{"attempts":3,"playable":18.258488418785124,"score":18.258488418785124},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":12.186252699594592,"score":8.124168466396394},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":32.23060098375562,"score":21.487067322503748}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:00:13Z","losses":4692,"max_score":45.99221229282847,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.2916666666666667,"model_code_failures":7,"model_display_name":"Mercury 2.5 Preview","model_slug":"inception-mercury-2-5-preview","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Inception","provider_key":"inception","rank":63,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:02:08Z","ranking_status":"ranked","rated_matches":8646,"rating_method":"bradley_terry_newton","raw_elo":1250.9058050062629,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inception","provider_model":"inception/mercury-2.5-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":4,"repaired_rate":0.16666666666666666,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":21.89213988063352,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":997},{"admitted_plugins":16,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-1-flash-lite:1403a2cbf671e1ab","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":24,"cost_basis_counts":{"provider_reported":50},"cost_is_complete":false,"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":97,"draws":1802,"eligibility_flag":false,"entry_count":16,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.1-flash-lite","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-08"],"first_pass_admitted":5,"first_pass_rate":0.20833333333333334,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":23.296932550117198,"score":15.531288366744798},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":42.804821402339726,"score":14.268273800779909},"GB2-03":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":43.33319183978524,"score":28.88879455985683},"GB2-05":{"attempts":3,"playable":11.244304065555825,"score":11.244304065555825},"GB2-06":{"attempts":3,"playable":22.050018355488657,"score":22.050018355488657},"GB2-07":{"attempts":3,"playable":14.186395681841859,"score":14.186395681841859},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":35.098817388849056,"score":23.399211592566036}},"ineligibility_reason_codes":["untested_or_ineligible_settings"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-25T23:46:16Z","losses":5532,"max_score":43.43520532438199,"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","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Google","provider_key":"google","rank":64,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"partial","rated_matches":8270,"rating_method":"bradley_terry_newton","raw_elo":876.5766784532934,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.1-flash-lite","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":11,"repaired_rate":0.4583333333333333,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":16.196035802854244,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":936},{"admitted_plugins":6,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:upstage-solar-mini4:08b83f586d8fd4ed","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":24,"cost_basis_counts":{"provider_reported":49},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":17,"max":0.02342595,"mean":0.008376991666666668,"median":0.0080226,"min":0.00063975,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":48},"recorded_attempt_count":49,"run_count":24,"total":0.20104779999999997},"codegen_evaluated_cells":23,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":95,"draws":437,"eligibility_flag":false,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"upstage/solar-mini4","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":2,"first_pass_rate":0.08695652173913043,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"failed_attempts":2,"playable":19.28125641080402,"score":6.427085470268007},"GB2-02":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-03":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-04":{"attempts":3,"failed_attempts":2,"playable":40.5751576693377,"score":13.5250525564459},"GB2-05":{"attempts":3,"failed_attempts":2,"playable":46.073471504282615,"score":15.357823834760872},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":25.7981729684762,"score":17.198781978984133},"GB2-07":{"attempts":3,"failed_attempts":2,"playable":33.11550594335333,"score":11.038501981117776},"GB2-08":{"attempts":3,"failed_attempts":3,"score":0.0}},"ineligibility_reason_codes":["below_generation_quality_threshold","generation_incomplete"],"infra_excluded_game_aliases":["GB2-02"],"infra_failures_excluded":1,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:19:36Z","losses":1952,"max_score":46.073471504282615,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.7391304347826086,"model_code_failures":17,"model_display_name":"Solar Mini 4","model_slug":"upstage-solar-mini4","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Upstage","provider_key":"upstage","rank":65,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"partial","rated_matches":3078,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"upstage","provider_model":"upstage/solar-mini4","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":4,"repaired_rate":0.17391304347826086,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":8.179035323783117,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":689},{"admitted_plugins":1,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:ibm-granite-granite-4-2-8b:dd8d48484dfe30a5","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":24,"cost_basis_counts":{"provider_reported":56},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":23,"max":0.01113168,"mean":0.00448752,"median":0.002935335,"min":0.00164236,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":37},"recorded_attempt_count":56,"run_count":24,"total":0.10770048000000002},"codegen_evaluated_cells":24,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":92,"draws":317,"eligibility_flag":false,"entry_count":1,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"ibm-granite/granite-4.2-8b","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":0,"first_pass_rate":0.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-02":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-03":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-04":{"attempts":3,"failed_attempts":2,"playable":38.83499052329622,"score":12.94499684109874},"GB2-05":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-06":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-07":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-08":{"attempts":3,"failed_attempts":3,"score":0.0}},"ineligibility_reason_codes":["below_generation_quality_threshold","fixed_coverage_incomplete","grouped_stability_incomplete"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T14:40:36Z","losses":154,"max_score":38.83499052329622,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.9583333333333334,"model_code_failures":23,"model_display_name":"Granite 4.2 8B","model_slug":"ibm-granite-granite-4-2-8b","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"IBM","provider_key":"ibm","rank":66,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"partial","rated_matches":498,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"ibm","provider_model":"ibm-granite/granite-4.2-8b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":1,"repaired_rate":0.041666666666666664,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":1.6181246051373426,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":27},{"admitted_plugins":8,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:unbiased-pareto-26-10:597e25e7df4b3ed3","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0450808,"mean":0.029576600000000005,"median":0.028589200000000002,"min":0.0192776,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":0.2366128},"codegen_evaluated_cells":8,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":96,"draws":263,"eligibility_flag":false,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"unbiased/pareto-26.10","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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},"headline_games":{"GB2-01":{"attempts":1,"playable":91.44446337962175,"score":91.44446337962175},"GB2-02":{"attempts":1,"playable":79.50804434894312,"score":79.50804434894312},"GB2-03":{"attempts":1,"playable":96.4292719023919,"score":96.4292719023919},"GB2-04":{"attempts":1,"playable":85.65291386041439,"score":85.65291386041439},"GB2-05":{"attempts":1,"playable":91.90017957529739,"score":91.90017957529739},"GB2-06":{"attempts":1,"playable":93.60240885205931,"score":93.60240885205931},"GB2-07":{"attempts":1,"playable":95.14792430503898,"score":95.14792430503898},"GB2-08":{"attempts":1,"playable":91.19045416553365,"score":91.19045416553365}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:27:19Z","losses":270,"max_score":96.4292719023919,"measured_at":null,"min_score":79.50804434894312,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Pareto 26.10","model_slug":"unbiased-pareto-26-10","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Unbiased","provider_key":"unbiased","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"unbiased","provider_model":"unbiased/pareto-26.10","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":90.60945754866256,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":3555},{"admitted_plugins":8,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:unbiased-pareto-26-10-preview:5bc5f373fda4e7ae","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0380352,"mean":0.030679699999999997,"median":0.0320616,"min":0.0216328,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.24543759999999998},"codegen_evaluated_cells":8,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":96,"draws":142,"eligibility_flag":false,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"unbiased/pareto-26.10-preview","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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},"headline_games":{"GB2-01":{"attempts":1,"playable":73.75996925502372,"score":73.75996925502372},"GB2-02":{"attempts":1,"playable":91.55797471857755,"score":91.55797471857755},"GB2-03":{"attempts":1,"playable":93.77026540100348,"score":93.77026540100348},"GB2-04":{"attempts":1,"playable":86.40302268825785,"score":86.40302268825785},"GB2-05":{"attempts":1,"playable":94.26076154257755,"score":94.26076154257755},"GB2-06":{"attempts":1,"playable":87.53442921211186,"score":87.53442921211186},"GB2-07":{"attempts":1,"playable":95.89865809396942,"score":95.89865809396942},"GB2-08":{"attempts":1,"playable":94.26598683752802,"score":94.26598683752802}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T15:40:41Z","losses":373,"max_score":95.89865809396942,"measured_at":null,"min_score":73.75996925502372,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Pareto 26.10 Preview","model_slug":"unbiased-pareto-26-10-preview","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Unbiased","provider_key":"unbiased","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"unbiased","provider_model":"unbiased/pareto-26.10-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":89.68138346863117,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":3573},{"admitted_plugins":16,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-pro:ebb0e62acb9965d6","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":16,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.158732805,"mean":0.032052512812499996,"median":0.0201057,"min":0.005105595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10,"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":19,"run_count":16,"total":0.512840205},"codegen_evaluated_cells":16,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":1402,"eligibility_flag":false,"entry_count":16,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"xiaomi/mimo-v2.6-pro","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":14,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":46.803893037375076,"score":46.803893037375076},"GB2-02":{"attempts":2,"playable":60.47446741056632,"score":60.47446741056632},"GB2-03":{"attempts":2,"playable":65.43384966484501,"score":65.43384966484501},"GB2-04":{"attempts":2,"playable":50.5320659191903,"score":50.5320659191903},"GB2-05":{"attempts":2,"playable":65.34674349348201,"score":65.34674349348201},"GB2-06":{"attempts":2,"playable":56.643631163108175,"score":56.643631163108175},"GB2-07":{"attempts":2,"playable":66.55602876764627,"score":66.55602876764627},"GB2-08":{"attempts":2,"playable":84.87944315574313,"score":84.87944315574313}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:55:21Z","losses":2546,"max_score":89.77514727559289,"measured_at":null,"min_score":39.5403292159651,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"MiMo-V2.6-Pro","model_slug":"xiaomi-mimo-v2-6-pro","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Xiaomi","provider_key":"xiaomi","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":8176,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.6-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":2,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":62.083765326494536,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":4228},{"admitted_plugins":2,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-5-preview:b267f0076fff90c1","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":2,"cell_count":3,"cost_basis_counts":{"provider_reported":5},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1898863,"mean":0.1851245,"median":0.183419,"min":0.1820682,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":4},"recorded_attempt_count":5,"run_count":3,"total":0.5553735},"codegen_evaluated_cells":2,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":94,"draws":277,"eligibility_flag":false,"entry_count":2,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"stepfun/step-5-preview","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":2,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-08":{"attempts":2,"playable":58.647177301731844,"score":58.647177301731844}},"ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:49:32Z","losses":331,"max_score":82.98469083668653,"measured_at":null,"min_score":34.30966376677716,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Step 5 Preview","model_slug":"stepfun-step-5-preview","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"StepFun","provider_key":"stepfun","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":1076,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"stepfun","provider_model":"stepfun/step-5-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":58.647177301731844,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":468},{"admitted_plugins":15,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-flash:93146796c36c7ec4","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":15,"cell_count":16,"cost_basis_counts":{"provider_reported":23},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02304638,"mean":0.01037612625,"median":0.0072198,"min":0.00188342,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":23},"recorded_attempt_count":23,"run_count":16,"total":0.16601801999999996},"codegen_evaluated_cells":16,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":1394,"eligibility_flag":false,"entry_count":15,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"xiaomi/mimo-v2.6-flash","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-04"],"first_pass_admitted":9,"first_pass_rate":0.5625,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":61.039510471904926,"score":61.039510471904926},"GB2-02":{"attempts":2,"playable":54.66579903193971,"score":54.66579903193971},"GB2-03":{"attempts":2,"playable":51.45163928679864,"score":51.45163928679864},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":58.70174355075301,"score":29.350871775376504},"GB2-05":{"attempts":2,"playable":56.40260350984238,"score":56.40260350984238},"GB2-06":{"attempts":2,"playable":58.7140786077428,"score":58.7140786077428},"GB2-07":{"attempts":2,"playable":61.97110724277714,"score":61.97110724277714},"GB2-08":{"attempts":2,"playable":29.356329172078745,"score":29.356329172078745}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:55:26Z","losses":3046,"max_score":83.23019220896973,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.0625,"model_code_failures":1,"model_display_name":"MiMo-V2.6-Flash","model_slug":"xiaomi-mimo-v2-6-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Xiaomi","provider_key":"xiaomi","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":7678,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.6-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":6,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":50.368992387307614,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":3238},{"admitted_plugins":16,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-flash:96faf37e1712a459","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":16,"cost_basis_counts":{"provider_reported":22},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.061982706,"mean":0.020562389374999997,"median":0.015992453,"min":0.0021123,"recorded_attempt_count":22,"run_count":16,"total":0.32899823},"codegen_evaluated_cells":16,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2151,"eligibility_flag":false,"entry_count":16,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.8-flash","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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},"headline_games":{"GB2-01":{"attempts":2,"playable":43.10777914544832,"score":43.10777914544832},"GB2-02":{"attempts":2,"playable":50.92272137182435,"score":50.92272137182435},"GB2-03":{"attempts":2,"playable":55.91884437113908,"score":55.91884437113908},"GB2-04":{"attempts":2,"playable":44.24324769256978,"score":44.24324769256978},"GB2-05":{"attempts":2,"playable":44.43466723481594,"score":44.43466723481594},"GB2-06":{"attempts":2,"playable":68.18876206730721,"score":68.18876206730721},"GB2-07":{"attempts":2,"playable":42.721336026580595,"score":42.721336026580595},"GB2-08":{"attempts":2,"playable":37.84466727169907,"score":37.84466727169907}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:57:06Z","losses":3336,"max_score":80.91204535467794,"measured_at":null,"min_score":10.143619159114431,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Qwen3.8 Flash","model_slug":"qwen-qwen3-8-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Alibaba","provider_key":"qwen","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":8176,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":6,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":48.42275314767305,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":2689},{"admitted_plugins":15,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-large-4-0:384cba7aa09bc4cf","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":15,"cell_count":16,"cost_basis_counts":{"provider_reported":23},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.33846634,"mean":0.10613685812499998,"median":0.05239252,"min":0.01134557,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":23},"recorded_attempt_count":23,"run_count":16,"total":1.69818973},"codegen_evaluated_cells":16,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2202,"eligibility_flag":false,"entry_count":15,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"mistralai/mistral-large-4-0","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-06"],"first_pass_admitted":11,"first_pass_rate":0.6875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":47.15376995777604,"score":47.15376995777604},"GB2-02":{"attempts":2,"playable":54.267767154668206,"score":54.267767154668206},"GB2-03":{"attempts":2,"playable":37.02602529219823,"score":37.02602529219823},"GB2-04":{"attempts":2,"playable":52.09864250433918,"score":52.09864250433918},"GB2-05":{"attempts":2,"playable":56.66657652051722,"score":56.66657652051722},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":79.63955354616625,"score":39.81977677308313},"GB2-07":{"attempts":2,"playable":44.486370931647215,"score":44.486370931647215},"GB2-08":{"attempts":2,"playable":42.43318297501246,"score":42.43318297501246}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T15:45:31Z","losses":2912,"max_score":79.63955354616625,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.0625,"model_code_failures":1,"model_display_name":"Mistral Large 4","model_slug":"mistralai-mistral-large-4-0","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Mistral","provider_key":"mistral","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":7674,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"mistral","provider_model":"mistralai/mistral-large-4-0","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":4,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":46.74401401365521,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":2560},{"admitted_plugins":13,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:elorian-glimpse:75e259dbabeebff6","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":23},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.224169,"mean":0.0821287125,"median":0.0481557,"min":0.0107334,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":23},"recorded_attempt_count":23,"run_count":16,"total":1.3140593999999999},"codegen_evaluated_cells":16,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":1341,"eligibility_flag":false,"entry_count":13,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"elorian/glimpse","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-05","GB2-06"],"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},"headline_games":{"GB2-01":{"attempts":2,"playable":47.88533845613112,"score":47.88533845613112},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.861474907777556,"score":21.930737453888778},"GB2-03":{"attempts":2,"playable":45.51502997852399,"score":45.51502997852399},"GB2-04":{"attempts":2,"playable":48.23535880825,"score":48.23535880825},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":58.69249200332186,"score":29.34624600166093},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":84.63629825457303,"score":42.31814912728652},"GB2-07":{"attempts":2,"playable":45.78585099453851,"score":45.78585099453851},"GB2-08":{"attempts":2,"playable":60.25543492210068,"score":60.25543492210068}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T14:24:48Z","losses":2618,"max_score":89.07242204112839,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.1875,"model_code_failures":3,"model_display_name":"Glimpse","model_slug":"elorian-glimpse","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Other","provider_key":"other","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":6664,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"elorian/glimpse","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":3,"repaired_rate":0.1875,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":42.659018217797566,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":2705},{"admitted_plugins":8,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1:a1e2894f4db70ea9","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":0.457564},"codegen_evaluated_cells":8,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":96,"draws":1090,"eligibility_flag":false,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-4.1","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":5,"first_pass_rate":0.625,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":61.84206851689213,"score":61.84206851689213},"GB2-02":{"attempts":1,"playable":42.910539295927805,"score":42.910539295927805},"GB2-03":{"attempts":1,"playable":39.302431406504134,"score":39.302431406504134},"GB2-04":{"attempts":1,"playable":38.63008847853202,"score":38.63008847853202},"GB2-05":{"attempts":1,"playable":13.93825891291957,"score":13.93825891291957},"GB2-06":{"attempts":1,"playable":50.13315219774284,"score":50.13315219774284},"GB2-07":{"attempts":1,"playable":47.98112150477692,"score":47.98112150477692},"GB2-08":{"attempts":1,"playable":44.442732998848115,"score":44.442732998848115}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:10Z","losses":1914,"max_score":61.84206851689213,"measured_at":null,"min_score":13.93825891291957,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GPT-4.1","model_slug":"gpt-4-1","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"OpenAI","provider_key":"openai","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":4087,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-4.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":42.397549164017946,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":1083},{"admitted_plugins":6,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k2-7-code:889b2709e6e0b012","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.2830031540000002},"codegen_evaluated_cells":7,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":96,"draws":694,"eligibility_flag":false,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"moonshotai/kimi-k2.7-code","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-06"],"first_pass_admitted":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},"headline_games":{"GB2-01":{"attempts":1,"playable":38.51497559923496,"score":38.51497559923496},"GB2-02":{"attempts":1,"playable":42.59335095030837,"score":42.59335095030837},"GB2-04":{"attempts":1,"playable":38.42514998716071,"score":38.42514998716071},"GB2-05":{"attempts":1,"playable":52.9753103538752,"score":52.9753103538752},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":43.523737593579355,"score":43.523737593579355},"GB2-08":{"attempts":1,"playable":68.29656182724565,"score":68.29656182724565}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"infra_excluded_game_aliases":["GB2-03"],"infra_failures_excluded":1,"is_recent_addition":false,"last_measured_at":"2026-10-25T23:51:26Z","losses":1337,"max_score":68.29656182724565,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.14285714285714285,"model_code_failures":1,"model_display_name":"Kimi K2.7 Code","model_slug":"moonshotai-kimi-k2-7-code","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Moonshot","provider_key":"moonshotai","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":3091,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k2.7-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":6,"repaired_rate":0.8571428571428571,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":40.61844090162918,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":1060},{"admitted_plugins":16,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-mini:60daed6b43fd9431","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":17,"cost_basis_counts":{"estimated":2,"local_standard_estimate":22},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":0.2156185632352941,"median":0.169101,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":22},"recorded_attempt_count":2,"run_count":18,"token_priced_attempt_count":22,"total":5.168810400000001},"codegen_evaluated_cells":16,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2449,"eligibility_flag":false,"entry_count":16,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.4-mini","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":13,"first_pass_rate":0.8125,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":51.819752220671134,"score":51.819752220671134},"GB2-02":{"attempts":2,"playable":41.53531315649431,"score":41.53531315649431},"GB2-03":{"attempts":2,"playable":45.52569905546824,"score":45.52569905546824},"GB2-04":{"attempts":2,"playable":43.89404994594723,"score":43.89404994594723},"GB2-05":{"attempts":2,"playable":29.526397279769263,"score":29.526397279769263},"GB2-06":{"attempts":2,"playable":39.334269029551784,"score":39.334269029551784},"GB2-07":{"attempts":2,"playable":26.179655135772354,"score":26.179655135772354},"GB2-08":{"attempts":2,"playable":33.483492076893796,"score":33.483492076893796}},"ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:58Z","losses":3979,"max_score":69.74557538933259,"measured_at":null,"min_score":6.4148569893735035,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GPT-5.4 Mini","model_slug":"gpt-5-4-mini","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"OpenAI","provider_key":"openai","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":8176,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4-mini","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":3,"repaired_rate":0.1875,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":38.91232848757102,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":1748},{"admitted_plugins":13,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5-pro:996de790147b6de7","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.2996388,"mean":0.08320818615,"median":0.048126608099999996,"min":0.0057139812,"recorded_attempt_count":28,"run_count":16,"total":1.3313309783999998},"codegen_evaluated_cells":14,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":1333,"eligibility_flag":false,"entry_count":13,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"xiaomi/mimo-v2.5-pro","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.2857142857142857,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":54.319662771015324,"score":54.319662771015324},"GB2-02":{"attempts":1,"playable":39.09761928198411,"score":39.09761928198411},"GB2-03":{"attempts":1,"playable":34.527363294170684,"score":34.527363294170684},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":47.60829699628472,"score":23.80414849814236},"GB2-05":{"attempts":2,"playable":22.383379426712345,"score":22.383379426712345},"GB2-06":{"attempts":2,"playable":52.78660997199282,"score":52.78660997199282},"GB2-07":{"attempts":2,"playable":45.55537993569061,"score":45.55537993569061},"GB2-08":{"attempts":2,"playable":23.94478687194261,"score":23.94478687194261}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"infra_excluded_game_aliases":["GB2-02","GB2-03"],"infra_failures_excluded":2,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:54Z","losses":3526,"max_score":71.37373256693535,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.07142857142857142,"model_code_failures":1,"model_display_name":"MiMo-V2.5-Pro","model_slug":"xiaomi-mimo-v2-5-pro","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Xiaomi","provider_key":"xiaomi","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":6704,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":9,"repaired_rate":0.6428571428571429,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":38.29903149795016,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":1845},{"admitted_plugins":14,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-max:8ba956e24bebbf1e","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.12185499999999999,"mean":0.05695140625,"median":0.036751875,"min":0.015285,"recorded_attempt_count":24,"run_count":16,"total":0.9112224999999998},"codegen_evaluated_cells":16,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":1878,"eligibility_flag":false,"entry_count":14,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.7-max","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03","GB2-04"],"first_pass_admitted":8,"first_pass_rate":0.5,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":42.23484043727251,"score":42.23484043727251},"GB2-02":{"attempts":2,"playable":45.127589240945326,"score":45.127589240945326},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":29.690595943558773,"score":14.845297971779386},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":43.63919085975499,"score":21.819595429877495},"GB2-05":{"attempts":2,"playable":38.080608175054834,"score":38.080608175054834},"GB2-06":{"attempts":2,"playable":38.78084228192538,"score":38.78084228192538},"GB2-07":{"attempts":2,"playable":68.61058634647813,"score":68.61058634647813},"GB2-08":{"attempts":2,"playable":31.28484283384198,"score":31.28484283384198}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:54Z","losses":3302,"max_score":76.16539028897841,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":2,"model_display_name":"Qwen3.7 Max","model_slug":"qwen-qwen3-7-max","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Alibaba","provider_key":"qwen","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":7185,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-max","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":6,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":37.59802533964688,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":2005},{"admitted_plugins":8,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-build-0-1:397ad047775cb684","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.48528460000000007},"codegen_evaluated_cells":8,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":96,"draws":1191,"eligibility_flag":false,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"x-ai/grok-build-0.1","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":0,"first_pass_rate":0.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":37.36459538989437,"score":37.36459538989437},"GB2-02":{"attempts":1,"playable":43.54460209735465,"score":43.54460209735465},"GB2-03":{"attempts":1,"playable":29.04587972921168,"score":29.04587972921168},"GB2-04":{"attempts":1,"playable":40.98421031880623,"score":40.98421031880623},"GB2-05":{"attempts":1,"playable":50.295915322236574,"score":50.295915322236574},"GB2-06":{"attempts":1,"playable":32.6755337727175,"score":32.6755337727175},"GB2-07":{"attempts":1,"playable":15.03523943046976,"score":15.03523943046976},"GB2-08":{"attempts":1,"playable":30.34812161583544,"score":30.34812161583544}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:35:05Z","losses":2163,"max_score":50.295915322236574,"measured_at":null,"min_score":15.03523943046976,"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","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"xAI","provider_key":"x-ai","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-build-0.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":8,"repaired_rate":1.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":34.91176220956577,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":734},{"admitted_plugins":1,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-1-flash:527a8fffe808ac75","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":2,"cost_basis_counts":{"provider_reported":3},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":3,"run_count":2,"total":0.0},"codegen_evaluated_cells":1,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":93,"draws":287,"eligibility_flag":false,"entry_count":1,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"inclusionai/ling-3.1-flash","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":1,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-08":{"attempts":1,"playable":33.32018896021172,"score":33.32018896021172}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T14:05:01Z","losses":229,"max_score":33.32018896021172,"measured_at":null,"min_score":33.32018896021172,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Ling 3.1 Flash","model_slug":"inclusionai-ling-3-1-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"InclusionAI","provider_key":"inclusionai","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":538,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.1-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":33.32018896021172,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":22},{"admitted_plugins":23,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:poolside-laguna-s-2-1:957df8aae5e922d8","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":16,"cost_basis_counts":{"provider_reported":68},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0068074,"mean":0.0032179299999999995,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":68,"run_count":28,"total":0.09094181999999999},"codegen_evaluated_cells":27,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2985,"eligibility_flag":false,"entry_count":23,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"poolside/laguna-s-2.1","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-04"],"first_pass_admitted":14,"first_pass_rate":0.5384615384615384,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":4,"failed_attempts":1,"playable":45.61939485793179,"score":35.38874268276867},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":42.01104720613089,"score":31.75957918894266},"GB2-03":{"attempts":4,"playable":39.102529841730124,"score":39.102529841730124},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":40.37057364428585,"score":20.185286822142924},"GB2-05":{"attempts":4,"playable":38.24152371387998,"score":38.24152371387998},"GB2-06":{"attempts":2,"playable":20.246889034093414,"score":20.246889034093414},"GB2-07":{"attempts":2,"playable":45.21795121798449,"score":45.21795121798449},"GB2-08":{"attempts":4,"playable":29.876980139390394,"score":29.876980139390394}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"infra_excluded_game_aliases":["GB2-04","GB2-06","GB2-07"],"infra_failures_excluded":5,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:39Z","losses":6123,"max_score":50.316181015211114,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.11538461538461539,"model_code_failures":3,"model_display_name":"Laguna S 2.1","model_slug":"poolside-laguna-s-2-1","performance_rejected_game_aliases":["GB2-07"],"performance_rejections":1,"plugin_success_rate":null,"provider":"Poolside","provider_key":"poolside","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":11798,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"poolside","provider_model":"poolside/laguna-s-2.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":9,"repaired_rate":0.34615384615384615,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":31.634760981160213,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":2690},{"admitted_plugins":13,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy3-preview:e70ee5ccebcd089b","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":25},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.007539277999999999,"mean":0.0022565913437500003,"median":0.0014932259999999998,"min":0.00090937,"recorded_attempt_count":25,"run_count":17,"total":0.041725612999999995},"codegen_evaluated_cells":17,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":1971,"eligibility_flag":false,"entry_count":13,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"tencent/hy3-preview","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03","GB2-05","GB2-06","GB2-07"],"first_pass_admitted":9,"first_pass_rate":0.5294117647058824,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":71.81343806792842,"score":71.81343806792842},"GB2-02":{"attempts":2,"playable":38.40745949264775,"score":38.40745949264775},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":32.17182072697564,"score":16.08591036348782},"GB2-04":{"attempts":2,"playable":45.97928982336829,"score":45.97928982336829},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":37.74596101507403,"score":22.693292624814305},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":14.277776758291424,"score":7.138888379145712},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":25.564044191476587,"score":12.782022095738293},"GB2-08":{"attempts":2,"playable":36.61539686104595,"score":36.61539686104595}},"ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:13Z","losses":3074,"max_score":78.40222463538099,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.23529411764705882,"model_code_failures":4,"model_display_name":"Hy3 Preview","model_slug":"tencent-hy3-preview","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Tencent","provider_key":"tencent","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":6650,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"tencent","provider_model":"tencent/hy3-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":4,"repaired_rate":0.23529411764705882,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":31.43946221352207,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":1605},{"admitted_plugins":11,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:nvidia-nemotron-3-5-super-vl:1cc2f77d42b49a10","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":11,"cell_count":16,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.017223799999999997,"mean":0.00762354625,"median":0.00630875,"min":0.0016103,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":26},"recorded_attempt_count":26,"run_count":16,"total":0.12197674},"codegen_evaluated_cells":16,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":1317,"eligibility_flag":false,"entry_count":11,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"nvidia/nemotron-3.5-super-vl","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-05","GB2-06"],"first_pass_admitted":6,"first_pass_rate":0.375,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":66.18873786369763,"score":33.09436893184881},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":44.81144895648299,"score":22.405724478241495},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":36.23182617727008,"score":18.11591308863504},"GB2-04":{"attempts":2,"playable":42.209823145404926,"score":42.209823145404926},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":58.31249676882345,"score":29.156248384411725},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":46.81810703397261,"score":23.409053516986305},"GB2-07":{"attempts":2,"playable":40.452956593532484,"score":40.452956593532484},"GB2-08":{"attempts":2,"playable":38.65960641776244,"score":38.65960641776244}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","below_generation_quality_threshold"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:50:40Z","losses":2589,"max_score":66.18873786369763,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.3125,"model_code_failures":5,"model_display_name":"Nemotron 3.5 Super Vl","model_slug":"nvidia-nemotron-3-5-super-vl","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"NVIDIA","provider_key":"nvidia","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":5654,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nvidia","provider_model":"nvidia/nemotron-3.5-super-vl","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":5,"repaired_rate":0.3125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":30.937961819602904,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":1748},{"admitted_plugins":37,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5:5058ed4f0f6da1c6","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":37,"cell_count":24,"cost_basis_counts":{"provider_reported":108},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0597184625,"mean":0.015888486455555555,"median":0.014928570933333333,"min":0.0016912200000000002,"recorded_attempt_count":108,"run_count":56,"total":0.7524538072},"codegen_evaluated_cells":44,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":5481,"eligibility_flag":false,"entry_count":37,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"xiaomi/mimo-v2.5","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-03","GB2-07","GB2-08"],"first_pass_admitted":13,"first_pass_rate":0.29545454545454547,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":6,"playable":32.04332823775294,"score":32.04332823775294},"GB2-02":{"attempts":7,"failed_attempts":2,"playable":42.56898646593197,"score":33.409501599366195},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":45.68133277644017,"score":15.227110925480057},"GB2-04":{"attempts":6,"playable":40.11943352075965,"score":40.11943352075965},"GB2-05":{"attempts":5,"playable":26.060840488137124,"score":26.060840488137124},"GB2-06":{"attempts":5,"playable":34.63021706681293,"score":34.63021706681293},"GB2-07":{"attempts":5,"failed_attempts":1,"playable":25.58105206875522,"score":22.17761998775572},"GB2-08":{"attempts":7,"failed_attempts":2,"playable":29.49415097817078,"score":22.229577311350877}},"ineligibility_reason_codes":["missing_or_non_distinct_settings","untested_or_ineligible_settings","generation_incomplete"],"infra_excluded_game_aliases":["GB2-01","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":12,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:11Z","losses":10144,"max_score":49.05847406271931,"measured_at":null,"min_score":13.613728323998012,"model_code_failure_rate":0.1590909090909091,"model_code_failures":7,"model_display_name":"MiMo-V2.5","model_slug":"xiaomi-mimo-v2-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Xiaomi","provider_key":"xiaomi","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":18948,"rating_method":"bradley_terry_newton","raw_elo":1289.80572023361,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":24,"repaired_rate":0.5454545454545454,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":30.69843243636994,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":3323},{"admitted_plugins":24,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-nano:8886fdcee94228f5","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":17,"cost_basis_counts":{"estimated":2,"local_standard_estimate":55},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":8,"max":0.26962149999999996,"mean":0.03182758529411764,"median":0.01676735,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":55},"recorded_attempt_count":2,"run_count":34,"token_priced_attempt_count":55,"total":1.0821378999999998},"codegen_evaluated_cells":32,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2169,"eligibility_flag":false,"entry_count":24,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.4-nano","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-03","GB2-04","GB2-07"],"first_pass_admitted":10,"first_pass_rate":0.3125,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":4,"playable":31.310180073622785,"score":31.310180073622785},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":40.290682020547486,"score":30.224634362579067},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":34.634106411260305,"score":8.658526602815076},"GB2-04":{"attempts":4,"failed_attempts":3,"playable":51.559785454938435,"score":12.889946363734609},"GB2-05":{"attempts":4,"playable":29.54827040042975,"score":29.54827040042975},"GB2-06":{"attempts":4,"playable":50.87951085446464,"score":50.87951085446464},"GB2-07":{"attempts":4,"failed_attempts":1,"playable":28.186873213149653,"score":22.878241620848495},"GB2-08":{"attempts":4,"playable":49.804761386688625,"score":49.804761386688625}},"ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:54:23Z","losses":6678,"max_score":60.18176763434397,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":8,"model_display_name":"GPT-5.4 Nano","model_slug":"gpt-5-4-nano","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"OpenAI","provider_key":"openai","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":12366,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4-nano","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":14,"repaired_rate":0.4375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":29.524258958147882,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":3519},{"admitted_plugins":14,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:google-gemma-4-31b-it:87daea4d942b603c","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":25},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0061656,"mean":0.0028540287500000002,"median":0.00232709,"min":0.0011068,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":25},"recorded_attempt_count":25,"run_count":16,"total":0.04566446},"codegen_evaluated_cells":16,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2197,"eligibility_flag":false,"entry_count":14,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemma-4-31b-it","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-03"],"first_pass_admitted":11,"first_pass_rate":0.6875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":22.403539400699408,"score":11.201769700349704},"GB2-02":{"attempts":2,"playable":41.69255892351879,"score":41.69255892351879},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":43.91462092939784,"score":21.95731046469892},"GB2-04":{"attempts":2,"playable":44.65758484118679,"score":44.65758484118679},"GB2-05":{"attempts":2,"playable":44.42844288715342,"score":44.42844288715342},"GB2-06":{"attempts":2,"playable":22.316293585053337,"score":22.316293585053337},"GB2-07":{"attempts":2,"playable":14.299755195825217,"score":14.299755195825217},"GB2-08":{"attempts":2,"playable":33.171670573651696,"score":33.171670573651696}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:59:02Z","losses":3838,"max_score":72.04104952761561,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":2,"model_display_name":"Gemma 4 31B","model_slug":"google-gemma-4-31b-it","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Google","provider_key":"google","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":7166,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemma-4-31b-it","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":3,"repaired_rate":0.1875,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":29.21567327142973,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":1131},{"admitted_plugins":26,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:meituan-longcat-2-0:9f72a9701d980346","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":16,"cost_basis_counts":{"provider_reported":108},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.103943664,"mean":0.050012701874999996,"median":0.041983026,"min":0.006392298,"recorded_attempt_count":108,"run_count":32,"total":1.60040646},"codegen_evaluated_cells":32,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2882,"eligibility_flag":false,"entry_count":26,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"meituan/longcat-2.0","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04"],"first_pass_admitted":17,"first_pass_rate":0.53125,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":4,"failed_attempts":2,"playable":42.64792367967752,"score":21.32396183983876},"GB2-02":{"attempts":4,"failed_attempts":2,"playable":41.85188882448263,"score":20.925944412241314},"GB2-03":{"attempts":4,"failed_attempts":1,"playable":37.182016067043776,"score":27.27734264352464},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":42.417917992853646,"score":30.795290583306937},"GB2-05":{"attempts":4,"playable":22.786710049563965,"score":22.786710049563965},"GB2-06":{"attempts":4,"playable":31.071116089179398,"score":31.071116089179398},"GB2-07":{"attempts":4,"playable":36.35384226617667,"score":36.35384226617667},"GB2-08":{"attempts":4,"playable":35.02893492150086,"score":35.02893492150086}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:43Z","losses":7614,"max_score":42.64792367967752,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.1875,"model_code_failures":6,"model_display_name":"LongCat 2.0","model_slug":"meituan-longcat-2-0","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Meituan","provider_key":"meituan","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":13367,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meituan","provider_model":"meituan/longcat-2.0","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":9,"repaired_rate":0.28125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":28.195392850666572,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":2871},{"admitted_plugins":13,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:minimax-minimax-m3:fdaffbd8b87d25c5","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":false,"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":0.7875583200000003},"codegen_evaluated_cells":16,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":1375,"eligibility_flag":false,"entry_count":13,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"minimax/minimax-m3","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03","GB2-04","GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.25,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":38.656854763493286,"score":38.656854763493286},"GB2-02":{"attempts":2,"playable":39.78711233554944,"score":39.78711233554944},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":39.9346947850152,"score":19.9673473925076},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":40.37057364428585,"score":20.185286822142924},"GB2-05":{"attempts":2,"playable":15.448223122742842,"score":15.448223122742842},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":17.1342988476045,"score":8.56714942380225},"GB2-07":{"attempts":2,"playable":33.00209595040792,"score":33.00209595040792},"GB2-08":{"attempts":2,"playable":38.38557527222924,"score":38.38557527222924}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:53:01Z","losses":3941,"max_score":58.7390484129797,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.1875,"model_code_failures":3,"model_display_name":"Minimax M3","model_slug":"minimax-minimax-m3","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"MiniMax","provider_key":"minimax","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":6682,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"minimax","provider_model":"minimax/minimax-m3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":9,"repaired_rate":0.5625,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":26.749955635359438,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":1366},{"admitted_plugins":12,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:nex-agi-nex-n2-pro:4d67cb8dc5f7cc0b","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":53},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.215758025,"mean":0.132049078125,"median":0.1281735,"min":0.061553000000000004,"recorded_attempt_count":53,"run_count":24,"total":3.40579925},"codegen_evaluated_cells":13,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":1313,"eligibility_flag":false,"entry_count":12,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"nex-agi/nex-n2-pro","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-04"],"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},"headline_games":{"GB2-02":{"attempts":1,"playable":36.228874289897526,"score":36.228874289897526},"GB2-03":{"attempts":2,"playable":33.08013719052168,"score":33.08013719052168},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":42.006158892138465,"score":21.003079446069233},"GB2-05":{"attempts":2,"playable":21.049285237346275,"score":21.049285237346275},"GB2-06":{"attempts":2,"playable":13.411822362801868,"score":13.411822362801868},"GB2-07":{"attempts":2,"playable":44.20649012084516,"score":44.20649012084516},"GB2-08":{"attempts":2,"playable":26.449219031603803,"score":26.449219031603803}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":11,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:57:28Z","losses":3815,"max_score":64.61361474216501,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.07692307692307693,"model_code_failures":1,"model_display_name":"Nex N2 Pro","model_slug":"nex-agi-nex-n2-pro","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Nex AGI","provider_key":"nex-agi","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":6166,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nex-agi","provider_model":"nex-agi/nex-n2-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":12,"repaired_rate":0.9230769230769231,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":26.46607328838344,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":1038},{"admitted_plugins":14,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-medium-3-5:fc6a8f8c064e1320","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"local_list_price_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.27741402547937455,"mean":0.12115799999999999,"median":0.10979066017348882,"min":0.04290565490575157,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":25},"run_count":16,"token_priced_attempt_count":25,"total":1.9385280000000003},"codegen_evaluated_cells":16,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":1976,"eligibility_flag":false,"entry_count":14,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"mistralai/mistral-medium-3-5","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-07"],"first_pass_admitted":7,"first_pass_rate":0.4375,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":12.087417348913485,"score":6.0437086744567425},"GB2-02":{"attempts":2,"playable":42.856105202140256,"score":42.856105202140256},"GB2-03":{"attempts":2,"playable":36.12228825217767,"score":36.12228825217767},"GB2-04":{"attempts":2,"playable":36.83188462793162,"score":36.83188462793162},"GB2-05":{"attempts":2,"playable":25.192232570742284,"score":25.192232570742284},"GB2-06":{"attempts":2,"playable":21.845226910235482,"score":21.845226910235482},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":13.007677305839454,"score":6.503838652919727},"GB2-08":{"attempts":2,"playable":31.636094235556904,"score":31.636094235556904}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:57:36Z","losses":4200,"max_score":44.600427873465655,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":2,"model_display_name":"Mistral Medium 3.5","model_slug":"mistralai-mistral-medium-3-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Mistral","provider_key":"mistral","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":7130,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"mistral","provider_model":"mistralai/mistral-medium-3-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":7,"repaired_rate":0.4375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":25.878922390770086,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":954},{"admitted_plugins":12,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-plus:ea2d2c42e42a55cb","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":false,"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":97,"draws":1505,"eligibility_flag":false,"entry_count":12,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.7-plus","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-03","GB2-04","GB2-08"],"first_pass_admitted":5,"first_pass_rate":0.29411764705882354,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":34.960339027005084,"score":30.215713743903656},"GB2-02":{"attempts":2,"playable":40.84466921239925,"score":40.84466921239925},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":43.76186614472562,"score":21.88093307236281},"GB2-05":{"attempts":2,"playable":38.07797660311408,"score":38.07797660311408},"GB2-06":{"attempts":2,"playable":42.51225085250504,"score":42.51225085250504},"GB2-07":{"attempts":2,"playable":16.2335780591337,"score":16.2335780591337},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":30.447266409765394,"score":15.223633204882697}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T00:54:23Z","losses":3376,"max_score":71.09088716682969,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.29411764705882354,"model_code_failures":5,"model_display_name":"Qwen3.7 Plus","model_slug":"qwen-qwen3-7-plus","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Alibaba","provider_key":"qwen","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":6151,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-plus","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":7,"repaired_rate":0.4117647058823529,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":25.62359434353766,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":1270},{"admitted_plugins":17,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-0-flash:27453f470337f222","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":16,"cost_basis_counts":{"provider_reported":96},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.00217964,"mean":0.00020429999999999998,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":96,"run_count":34,"total":0.0098064},"codegen_evaluated_cells":23,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":2542,"eligibility_flag":false,"entry_count":17,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"inclusionai/ling-3.0-flash","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-04","GB2-05","GB2-07"],"first_pass_admitted":8,"first_pass_rate":0.34782608695652173,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":27.575023019871132,"score":27.575023019871132},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":39.043454069275995,"score":28.897924103696923},"GB2-03":{"attempts":2,"playable":28.97412060092674,"score":28.97412060092674},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":42.309890175760486,"score":31.145267897827352},"GB2-05":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-06":{"attempts":3,"playable":14.633638438814337,"score":14.633638438814337},"GB2-07":{"attempts":4,"failed_attempts":2,"playable":35.974658495177195,"score":17.987329247588598},"GB2-08":{"attempts":3,"playable":33.38373127258608,"score":33.38373127258608}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-08"],"infra_failures_excluded":10,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:03:01Z","losses":4925,"max_score":39.96129123978842,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.2608695652173913,"model_code_failures":6,"model_display_name":"Ling 3.0 Flash","model_slug":"inclusionai-ling-3-0-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"InclusionAI","provider_key":"inclusionai","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":8672,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.0-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":9,"repaired_rate":0.391304347826087,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":24.65642061462963,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":1205},{"admitted_plugins":7,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:recursive-flint-v1-0:4c67da8b97724824","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.0},"codegen_evaluated_cells":8,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":96,"draws":733,"eligibility_flag":false,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"unknown_legacy","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"recursive/flint-v1.0","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03"],"first_pass_admitted":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},"headline_games":{"GB2-01":{"attempts":1,"playable":44.76413372751087,"score":44.76413372751087},"GB2-02":{"attempts":1,"playable":35.05804086751001,"score":35.05804086751001},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":39.75659327595914,"score":39.75659327595914},"GB2-05":{"attempts":1,"playable":13.93825891291957,"score":13.93825891291957},"GB2-06":{"attempts":1,"playable":17.020471221862483,"score":17.020471221862483},"GB2-07":{"attempts":1,"playable":10.34922351327472,"score":10.34922351327472},"GB2-08":{"attempts":1,"playable":28.066626976915888,"score":28.066626976915888}},"ineligibility_reason_codes":["missing_bracket_scores","unknown_capability_evidence","missing_generation_quality"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:56Z","losses":2329,"max_score":44.76413372751087,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"Flint V1.0","model_slug":"recursive-flint-v1-0","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Other","provider_key":"other","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":3594,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"recursive/flint-v1.0","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":23.619168561994087,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":532},{"admitted_plugins":5,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:nex-agi-nex-n2-5-pro:fccb1b6c33bebb4e","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":5,"cell_count":24,"cost_basis_counts":{"provider_reported":38},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.02555855,"mean":0.0050213301041666675,"median":0.00152996375,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":23},"recorded_attempt_count":38,"run_count":27,"total":0.121453125},"codegen_evaluated_cells":10,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":96,"draws":498,"eligibility_flag":false,"entry_count":5,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"nex-agi/nex-n2.5-pro","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-03","GB2-04","GB2-05","GB2-06"],"first_pass_admitted":5,"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},"headline_games":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":37.504788276235715,"score":37.504788276235715},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":45.88861566334852,"score":22.94430783167426},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":2,"playable":38.056689293189194,"score":38.056689293189194},"GB2-08":{"attempts":1,"playable":30.843798288708303,"score":30.843798288708303}},"ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality","below_generation_quality_threshold","generation_incomplete"],"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-04","GB2-05","GB2-06","GB2-08"],"infra_failures_excluded":6,"is_recent_addition":false,"last_measured_at":"2026-10-24T14:00:28Z","losses":1414,"max_score":45.88861566334852,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.5,"model_code_failures":5,"model_display_name":"Nex N2.5 Pro","model_slug":"nex-agi-nex-n2-5-pro","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Nex AGI","provider_key":"nex-agi","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":2572,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nex-agi","provider_model":"nex-agi/nex-n2.5-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":19.636154322163883,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":660},{"admitted_plugins":9,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:cohere-north-mini-code:6e98d5379eb035a9","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":9,"cell_count":16,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":15},"recorded_attempt_count":30,"run_count":16,"total":0.0},"codegen_evaluated_cells":16,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":97,"draws":815,"eligibility_flag":false,"entry_count":9,"evaluated_setting_identity":{"canonical_provider_route":"unknown_legacy","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"cohere/north-mini-code","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-06"],"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},"headline_games":{"GB2-01":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-02":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":21.734159723041202,"score":10.867079861520601},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":41.18867852179604,"score":20.59433926089802},"GB2-05":{"attempts":2,"playable":33.17170468869959,"score":33.17170468869959},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":17.24808744063479,"score":8.624043720317395},"GB2-07":{"attempts":2,"playable":16.12436846729509,"score":16.12436846729509},"GB2-08":{"attempts":2,"playable":30.942760279976877,"score":30.942760279976877}},"ineligibility_reason_codes":["missing_bracket_scores","unknown_capability_evidence","missing_generation_quality","below_generation_quality_threshold"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-08-05T05:19:01Z","losses":3119,"max_score":46.457859448926094,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.4375,"model_code_failures":7,"model_display_name":"North Mini Code","model_slug":"cohere-north-mini-code","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"Cohere","provider_key":"cohere","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":4690,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"cohere","provider_model":"cohere/north-mini-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":4,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":15.040537034838447,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":756},{"admitted_plugins":3,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1-nano:c8bc28f37863669f","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":5,"max":0.0034966000000000003,"mean":0.002188375,"median":0.0022738000000000003,"min":0.0011728,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"run_count":8,"token_priced_attempt_count":13,"total":0.017507},"codegen_evaluated_cells":8,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":93,"draws":680,"eligibility_flag":false,"entry_count":3,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"aggregate","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-4.1-nano","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"unknown_legacy","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-04","GB2-05","GB2-07","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},"headline_games":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":41.32357014605849,"score":41.32357014605849},"GB2-03":{"attempts":1,"playable":35.16739412202156,"score":35.16739412202156},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":17.929981650115,"score":17.929981650115},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","below_generation_quality_threshold"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T14:25:19Z","losses":713,"max_score":41.32357014605849,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.625,"model_code_failures":5,"model_display_name":"GPT-4.1 Nano","model_slug":"gpt-4-1-nano","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":null,"provider":"OpenAI","provider_key":"openai","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":1476,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":null,"reasoning_level":"Overall Models","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-4.1-nano","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null},"reasoning_setting":null,"repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":11.802618239774382,"score_basis":"mean of available official reasoning-group scores","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"overall","track_name":"Overall Models","uncertainty":null,"unilateral_faults":null,"wins":83}],"schema_version":12,"snapshot_id":"20261026_022724","track_id":"overall"}